Add files via upload

Engine/Properties/scanner.py

@@ -0,0 +1,545 @@
+import os, sys, math, json, pefile, datetime
+import numpy as np
+import onnxruntime as ort
+import ctypes, ctypes.wintypes
+
+####################################################################################################
+
+MODEL_FILE = "Pefile_General_S1.onnx"
+FEATURE_FILE = "features.json"
+MAX_FILE_SIZE = 4 * 1024 * 1024 * 1024
+TARGET_EXTENSIONS = {
+    '.exe', '.dll', '.sys', '.ocx', '.scr', '.efi', '.acm', '.ax', '.cpl', '.drv', '.com', '.mui', '.pyd'
+}
+
+####################################################################################################
+
+class WINTRUST_FILE_INFO(ctypes.Structure):
+    _fields_ = [
+        ("cbStruct", ctypes.wintypes.DWORD),
+        ("pcwszFilePath", ctypes.wintypes.LPCWSTR),
+        ("hFile", ctypes.wintypes.HANDLE),
+        ("pgKnownSubject", ctypes.wintypes.LPVOID)
+    ]
+
+class WINTRUST_DATA_UNION(ctypes.Union):
+    _fields_ = [
+        ("pFile", ctypes.POINTER(WINTRUST_FILE_INFO)),
+        ("pCatalog", ctypes.wintypes.LPVOID),
+        ("pBlob", ctypes.wintypes.LPVOID),
+        ("pSgnr", ctypes.wintypes.LPVOID),
+        ("pCert", ctypes.wintypes.LPVOID)
+    ]
+
+class WINTRUST_DATA(ctypes.Structure):
+    _fields_ = [
+        ("cbStruct", ctypes.wintypes.DWORD),
+        ("pPolicyCallbackData", ctypes.wintypes.LPVOID),
+        ("pSIPClientData", ctypes.wintypes.LPVOID),
+        ("dwUIChoice", ctypes.wintypes.DWORD),
+        ("fdwRevocationChecks", ctypes.wintypes.DWORD),
+        ("dwUnionChoice", ctypes.wintypes.DWORD),
+        ("u", WINTRUST_DATA_UNION),
+        ("dwStateAction", ctypes.wintypes.DWORD),
+        ("hWVTStateData", ctypes.wintypes.HANDLE),
+        ("pwszURLReference", ctypes.wintypes.LPCWSTR),
+        ("dwProvFlags", ctypes.wintypes.DWORD),
+        ("dwUIContext", ctypes.wintypes.DWORD),
+        ("pSignatureSettings", ctypes.wintypes.LPVOID)
+    ]
+
+class GUID(ctypes.Structure):
+    _fields_ = [
+        ("Data1", ctypes.wintypes.DWORD),
+        ("Data2", ctypes.wintypes.WORD),
+        ("Data3", ctypes.wintypes.WORD),
+        ("Data4", ctypes.c_ubyte * 8)
+    ]
+
+V2_GUID = GUID(0x00AAC56B, 0xCD44, 0x11D0, (ctypes.c_ubyte * 8)(0x8C, 0xC2, 0x00, 0xC0, 0x4F, 0xC2, 0x95, 0xEE))
+
+####################################################################################################
+
+class WinTrust:
+    @staticmethod
+    def verify(file_path):
+        if os.name != 'nt':
+            return 0
+        try:
+            wintrust = ctypes.windll.wintrust
+            wintrust.WinVerifyTrust.argtypes = [ctypes.wintypes.HWND, ctypes.POINTER(GUID), ctypes.wintypes.LPVOID]
+            wintrust.WinVerifyTrust.restype = ctypes.wintypes.LONG
+
+            fi = WINTRUST_FILE_INFO()
+            fi.cbStruct = ctypes.sizeof(WINTRUST_FILE_INFO)
+            fi.pcwszFilePath = os.path.abspath(file_path)
+            fi.hFile = None
+            fi.pgKnownSubject = None
+
+            wt_union = WINTRUST_DATA_UNION()
+            wt_union.pFile = ctypes.pointer(fi)
+
+            td = WINTRUST_DATA()
+            td.cbStruct = ctypes.sizeof(WINTRUST_DATA)
+            td.pPolicyCallbackData = None
+            td.pSIPClientData = None
+            td.dwUIChoice = 2
+            td.fdwRevocationChecks = 0
+            td.dwUnionChoice = 1
+            td.u = wt_union
+            td.dwStateAction = 0
+            td.hWVTStateData = None
+            td.pwszURLReference = None
+            td.dwProvFlags = 0
+            td.dwUIContext = 0
+            td.pSignatureSettings = None
+
+            return 1 if wintrust.WinVerifyTrust(None, ctypes.byref(V2_GUID), ctypes.byref(td)) == 0 else 0
+        except Exception:
+            return 0
+
+####################################################################################################
+
+class FeatureExtractor:
+    @staticmethod
+    def _safe_float(val):
+        try:
+            f = float(val)
+            return f if not (math.isinf(f) or math.isnan(f)) else 0.0
+        except Exception: 
+            return 0.0
+
+    @staticmethod
+    def _calc_entropy(data):
+        if not data: return 0.0
+        import numpy as np
+        arr = np.frombuffer(data, dtype=np.uint8)
+        counts = np.bincount(arr, minlength=256)
+        probs = counts[counts > 0] / len(arr)
+        return float(-np.sum(probs * np.log2(probs)))
+
+    @classmethod
+    def _extract_overlay_features(cls, pe, fsize):
+        overlay_offset = pe.get_overlay_data_start_offset()
+        if not overlay_offset or overlay_offset >= fsize:
+            return {"HasOverlay": 0.0, "OverlaySize": 0.0, "OverlayRatio": 0.0, "OverlayEntropy": 0.0}
+        
+        overlay_data = pe.get_overlay()
+        if not overlay_data:
+            return {"HasOverlay": 0.0, "OverlaySize": 0.0, "OverlayRatio": 0.0, "OverlayEntropy": 0.0}
+
+        sz = len(overlay_data)
+        return {
+            "HasOverlay": 1.0,
+            "OverlaySize": float(sz),
+            "OverlayRatio": float(sz) / float(fsize),
+            "OverlayEntropy": cls._calc_entropy(overlay_data)
+        }
+
+    @classmethod
+    def _extract_rich_header(cls, pe):
+        if not hasattr(pe, 'RICH_HEADER') or not pe.RICH_HEADER:
+            return {"HasRichHeader": 0.0, "RichHeaderCount": 0.0}
+        return {
+            "HasRichHeader": 1.0,
+            "RichHeaderCount": float(len(pe.RICH_HEADER.values) // 2) if hasattr(pe.RICH_HEADER, 'values') else 0.0
+        }
+
+    @classmethod
+    def _extract_ep_anomalies(cls, pe):
+        if not hasattr(pe, 'OPTIONAL_HEADER') or not hasattr(pe, 'sections') or not pe.sections:
+            return {"EntryPointSectionIndex": -1.0, "EntryPointInExecutable": 0.0, "EntryPointInLastSection": 0.0}
+
+        ep = pe.OPTIONAL_HEADER.AddressOfEntryPoint
+        ep_section_idx = -1
+        ep_in_exec = 0.0
+        
+        for idx, sec in enumerate(pe.sections):
+            if sec.VirtualAddress <= ep < (sec.VirtualAddress + sec.Misc_VirtualSize):
+                ep_section_idx = idx
+                if sec.Characteristics & 0x20000000:
+                    ep_in_exec = 1.0
+                break
+                
+        return {
+            "EntryPointSectionIndex": float(ep_section_idx),
+            "EntryPointInExecutable": ep_in_exec,
+            "EntryPointInLastSection": 1.0 if ep_section_idx == len(pe.sections) - 1 else 0.0
+        }
+
+    @classmethod
+    def _extract_advanced_resources(cls, pe):
+        res_data = {
+            "ResourceMaxEntropy": 0.0,
+            "ResourceMinEntropy": 0.0,
+            "ResourceMeanEntropy": 0.0,
+            "ResourceLangCount": 0.0,
+            "ResourceRCDataCount": 0.0
+        }
+        
+        if not hasattr(pe, 'DIRECTORY_ENTRY_RESOURCE'):
+            return res_data
+            
+        entropies = []
+        langs = set()
+        rcdata_count = 0
+        
+        for entry_type in pe.DIRECTORY_ENTRY_RESOURCE.entries:
+            if hasattr(entry_type, 'id') and entry_type.id == 10: 
+                rcdata_count += len(getattr(entry_type.directory, 'entries', []))
+                
+            if not hasattr(entry_type, 'directory'):
+                continue
+                
+            for entry_id in entry_type.directory.entries:
+                if not hasattr(entry_id, 'directory'):
+                    continue
+                    
+                for entry_lang in entry_id.directory.entries:
+                    if hasattr(entry_lang, 'id'):
+                        langs.add(entry_lang.id)
+                    if hasattr(entry_lang, 'data'):
+                        try:
+                            data = pe.get_data(entry_lang.data.struct.OffsetToData, entry_lang.data.struct.Size)
+                            entropies.append(cls._calc_entropy(data))
+                        except Exception:
+                            continue
+                            
+        res_data["ResourceLangCount"] = float(len(langs))
+        res_data["ResourceRCDataCount"] = float(rcdata_count)
+        
+        if entropies:
+            res_data["ResourceMaxEntropy"] = max(entropies)
+            res_data["ResourceMinEntropy"] = min(entropies)
+            res_data["ResourceMeanEntropy"] = sum(entropies) / len(entropies)
+            
+        return res_data
+
+    @classmethod
+    def _extract_load_config(cls, pe):
+        cfg = {"HasLoadConfig": 0.0, "HasCFG": 0.0, "HasSEHTable": 0.0}
+        if hasattr(pe, 'DIRECTORY_ENTRY_LOAD_CONFIG'):
+            cfg["HasLoadConfig"] = 1.0
+            struct = pe.DIRECTORY_ENTRY_LOAD_CONFIG.struct
+            if getattr(struct, 'GuardCFFunctionTable', 0) != 0:
+                cfg["HasCFG"] = 1.0
+            if getattr(struct, 'SEHandlerTable', 0) != 0:
+                cfg["HasSEHTable"] = 1.0
+        return cfg
+
+    @classmethod
+    def extract(cls, file_path):
+        pe = None
+        try:
+            fsize = os.path.getsize(file_path)
+            if fsize == 0 or fsize > MAX_FILE_SIZE: 
+                return None
+
+            with open(file_path, "rb") as f:
+                file_bytes = f.read()
+
+            base, dlls, apis = {}, set(), set()
+            pe = pefile.PE(data=file_bytes, fast_load=True)
+            
+            base['TrustSigned'] = float(WinTrust.verify(file_path))
+            base['FileEntropy'] = cls._calc_entropy(file_bytes)
+            base['FileSize'] = float(fsize)
+            
+            fh = pe.FILE_HEADER
+            base['Machine'] = getattr(fh, 'Machine', 0)
+            base['NumberOfSections'] = getattr(fh, 'NumberOfSections', 0)
+            base['TimeDateStamp'] = getattr(fh, 'TimeDateStamp', 0)
+            base['PointerToSymbolTable'] = getattr(fh, 'PointerToSymbolTable', 0)
+            base['NumberOfSymbols'] = getattr(fh, 'NumberOfSymbols', 0)
+            base['SizeOfOptionalHeader'] = getattr(fh, 'SizeOfOptionalHeader', 0)
+            base['Characteristics'] = getattr(fh, 'Characteristics', 0)
+
+            curr_ts = datetime.datetime.utcnow().timestamp()
+            base['HasInvalidTimestamp'] = 1.0 if (base['TimeDateStamp'] < 631152000 or base['TimeDateStamp'] > curr_ts + 2592000) else 0.0
+            base['FileTimeException'] = 1.0 if base['TimeDateStamp'] == 0 else 0.0
+            base['Is64Bit'] = 1.0 if base['Machine'] in (0x8664, 0xAA64, 0x0200) else 0.0
+            base['IsExe'] = 1.0 if pe.is_exe() else 0.0
+            base['IsDll'] = 1.0 if pe.is_dll() else 0.0
+
+            base['ExceptionCount'] = 0.0
+
+            if hasattr(pe, 'OPTIONAL_HEADER'):
+                op = pe.OPTIONAL_HEADER
+                fields = ['Magic', 'MajorLinkerVersion', 'MinorLinkerVersion', 'SizeOfCode', 'SizeOfInitializedData', 'SizeOfUninitializedData', 'AddressOfEntryPoint', 'BaseOfCode', 'ImageBase', 'SectionAlignment', 'FileAlignment', 'MajorOperatingSystemVersion', 'MinorOperatingSystemVersion', 'MajorImageVersion', 'MinorImageVersion', 'MajorSubsystemVersion', 'MinorSubsystemVersion', 'SizeOfImage', 'SizeOfHeaders', 'CheckSum', 'Subsystem', 'DllCharacteristics', 'SizeOfStackReserve', 'SizeOfStackCommit', 'SizeOfHeapReserve', 'SizeOfHeapCommit', 'LoaderFlags', 'NumberOfRvaAndSizes']
+                for f in fields: base[f] = getattr(op, f, 0)
+                base['IsDriver'] = 1.0 if base.get('Subsystem') == 1 else 0.0
+
+                if hasattr(op, 'DATA_DIRECTORY'):
+                    for i, directory in enumerate(op.DATA_DIRECTORY):
+                        base[f'DataDirectory_{i}_Size'] = directory.Size
+                        base[f'DataDirectory_{i}_VA'] = directory.VirtualAddress
+                    
+                    exc_idx = pefile.DIRECTORY_ENTRY.get('IMAGE_DIRECTORY_ENTRY_EXCEPTION', 3)
+                    if len(op.DATA_DIRECTORY) > exc_idx and op.DATA_DIRECTORY[exc_idx].Size > 0:
+                        base['ExceptionCount'] = op.DATA_DIRECTORY[exc_idx].Size // 12 if base['Machine'] in (0x8664, 0xAA64) else 0.0
+
+            char_flags = [0x00000020, 0x00000040, 0x00000080, 0x02000000, 0x20000000, 0x40000000, 0x80000000]
+            for flag in char_flags:
+                base[f'Char_{flag:08X}_Count'] = 0.0
+                base[f'Char_{flag:08X}_MeanEntropy'] = 0.0
+
+            if hasattr(pe, 'sections'):
+                base['SectionCount'] = len(pe.sections)
+                entropies, raw_sizes, v_sizes = [], [], []
+                exec_sec, write_sec, read_sec, sec_exc = 0, 0, 0, 0
+                
+                for section in pe.sections:
+                    try:
+                        s_data = section.get_data()
+                        s_entropy = cls._calc_entropy(s_data)
+                    except Exception: 
+                        s_entropy = 0.0
+
+                    entropies.append(s_entropy)
+                    raw_sizes.append(section.SizeOfRawData)
+                    v_sizes.append(section.Misc_VirtualSize)
+
+                    if section.Characteristics & 0x20000000: exec_sec += 1
+                    if section.Characteristics & 0x80000000: write_sec += 1
+                    if section.Characteristics & 0x40000000: read_sec += 1
+                    if section.SizeOfRawData + section.PointerToRawData > fsize: sec_exc = 1
+
+                    for flag in char_flags:
+                        if section.Characteristics & flag:
+                            base[f'Char_{flag:08X}_Count'] += 1.0
+                            base[f'Char_{flag:08X}_MeanEntropy'] += s_entropy
+
+                base['SectionMaxEntropy'] = max(entropies) if entropies else 0.0
+                base['SectionMinEntropy'] = min(entropies) if entropies else 0.0
+                base['SectionMeanEntropy'] = sum(entropies) / len(entropies) if entropies else 0.0
+                base['SectionMaxRawSize'] = max(raw_sizes) if raw_sizes else 0.0
+                base['SectionMinRawSize'] = min(raw_sizes) if raw_sizes else 0.0
+                base['SectionMeanRawSize'] = sum(raw_sizes) / len(raw_sizes) if raw_sizes else 0.0
+                base['SectionMaxVSize'] = max(v_sizes) if v_sizes else 0.0
+                base['SectionMinVSize'] = min(v_sizes) if v_sizes else 0.0
+                base['SectionMeanVSize'] = sum(v_sizes) / len(v_sizes) if v_sizes else 0.0
+                base['ExecutableSections'] = exec_sec
+                base['WritableSections'] = write_sec
+                base['ReadableSections'] = read_sec
+                base['SectionException'] = float(sec_exc)
+
+                for flag in char_flags:
+                    if base[f'Char_{flag:08X}_Count'] > 0:
+                        base[f'Char_{flag:08X}_MeanEntropy'] = base[f'Char_{flag:08X}_MeanEntropy'] / base[f'Char_{flag:08X}_Count']
+
+            string_keys = ['FileDescription', 'FileVersion', 'ProductName', 'ProductVersion', 'CompanyName', 'LegalCopyright', 'Comments', 'InternalName', 'LegalTrademarks', 'SpecialBuild', 'PrivateBuild']
+            for key in string_keys: 
+                base[f'{key}Length'] = 0.0
+                
+            if hasattr(pe, 'FileInfo'):
+                for fileinfo_list in pe.FileInfo:
+                    for fileinfo in fileinfo_list:
+                        if getattr(fileinfo, 'name', '') in ('StringFileInfo', b'StringFileInfo'):
+                            for st in getattr(fileinfo, 'StringTable', []):
+                                for key, val in st.entries.items():
+                                    try:
+                                        k = key.decode('utf-8', 'ignore') if isinstance(key, bytes) else str(key)
+                                        if k in string_keys:
+                                            v = val.decode('utf-8', 'ignore') if isinstance(val, bytes) else str(val)
+                                            base[f'{k}Length'] = float(len(v))
+                                    except Exception: 
+                                        continue
+
+            try: 
+                pe.parse_data_directories(directories=[
+                    pefile.DIRECTORY_ENTRY['IMAGE_DIRECTORY_ENTRY_IMPORT'], 
+                    pefile.DIRECTORY_ENTRY['IMAGE_DIRECTORY_ENTRY_EXPORT'], 
+                    pefile.DIRECTORY_ENTRY['IMAGE_DIRECTORY_ENTRY_RESOURCE'], 
+                    pefile.DIRECTORY_ENTRY['IMAGE_DIRECTORY_ENTRY_DEBUG'], 
+                    pefile.DIRECTORY_ENTRY['IMAGE_DIRECTORY_ENTRY_TLS'],
+                    pefile.DIRECTORY_ENTRY['IMAGE_DIRECTORY_ENTRY_LOAD_CONFIG']
+                ])
+            except Exception: pass
+
+            if hasattr(pe, 'DIRECTORY_ENTRY_TLS') and hasattr(pe.DIRECTORY_ENTRY_TLS, 'struct'):
+                base['HasTlsCallbacks'] = 1.0 if getattr(pe.DIRECTORY_ENTRY_TLS.struct, 'AddressOfCallBacks', 0) != 0 else 0.0
+            
+            if hasattr(pe, 'VS_FIXEDFILEINFO') and len(pe.VS_FIXEDFILEINFO) > 0:
+                flags = getattr(pe.VS_FIXEDFILEINFO[0], 'FileFlags', 0)
+                base['IsDebug'] = 1.0 if flags & 0x1 else 0.0
+                base['IsPreRelease'] = 1.0 if flags & 0x2 else 0.0
+                base['IsPatched'] = 1.0 if flags & 0x4 else 0.0
+                base['IsPrivateBuild'] = 1.0 if flags & 0x8 else 0.0
+                base['IsSpecialBuild'] = 1.0 if flags & 0x20 else 0.0
+
+            if hasattr(pe, 'DIRECTORY_ENTRY_IMPORT'):
+                base['ImportCount'] = len(pe.DIRECTORY_ENTRY_IMPORT)
+                func_count = 0
+                for entry in pe.DIRECTORY_ENTRY_IMPORT:
+                    if getattr(entry, 'dll', None):
+                        try: dlls.add(entry.dll.decode('ascii', 'ignore').lower())
+                        except Exception: pass
+                    for imp in getattr(entry, 'imports', []):
+                        func_count += 1
+                        if getattr(imp, 'name', None):
+                            try: apis.add(imp.name.decode('ascii', 'ignore'))
+                            except Exception: pass
+                base['ImportFunctionCount'] = func_count
+
+            base['ExportCount'] = len(pe.DIRECTORY_ENTRY_EXPORT.symbols) if (hasattr(pe, 'DIRECTORY_ENTRY_EXPORT') and hasattr(pe.DIRECTORY_ENTRY_EXPORT, 'symbols')) else 0.0
+
+            if hasattr(pe, 'DIRECTORY_ENTRY_RESOURCE'):
+                icon_count = 0
+                for entry in pe.DIRECTORY_ENTRY_RESOURCE.entries:
+                    if getattr(entry, 'id', None) == 3 and hasattr(entry, 'directory'):
+                        icon_count += len(getattr(entry.directory, 'entries', []))
+                base['IconCount'] = icon_count
+            else: 
+                base['IconCount'] = 0.0
+
+            base['DebugCount'] = len(pe.DIRECTORY_ENTRY_DEBUG) if hasattr(pe, 'DIRECTORY_ENTRY_DEBUG') else 0.0
+
+            base.update(cls._extract_overlay_features(pe, fsize))
+            base.update(cls._extract_rich_header(pe))
+            base.update(cls._extract_ep_anomalies(pe))
+            base.update(cls._extract_advanced_resources(pe))
+            base.update(cls._extract_load_config(pe))
+
+            for k in base: base[k] = cls._safe_float(base[k])
+            return {"Base": base, "DLLs": list(dlls), "APIs": list(apis)}
+
+        except Exception: return None
+        finally:
+            if pe: pe.close()
+
+####################################################################################################
+
+class ModelPredictor:
+    def __init__(self, model_path, feature_path):
+        self.model_features = self._load_features(feature_path)
+        self.sess = ort.InferenceSession(model_path, providers=['CPUExecutionProvider'])
+        self.input_name = self.sess.get_inputs()[0].name
+        
+        expected_dim = self.sess.get_inputs()[0].shape[1]
+        current_dim = len(self.model_features)
+        if current_dim != expected_dim:
+            raise ValueError(f"Dimension mismatch! Model expects {expected_dim} features, but feature file lists {current_dim}.")
+
+    def _load_features(self, path):
+        if not os.path.exists(path):
+            raise FileNotFoundError(f"Feature file not found: {path}")
+        with open(path, 'r') as f:
+            return json.load(f)
+
+    def predict(self, raw_data):
+        vec = np.zeros((1, len(self.model_features)), dtype=np.float32)
+        base = raw_data.get('Base', {})
+        dlls = set(raw_data.get('DLLs', []))
+        apis = set(raw_data.get('APIs', []))
+
+        for i, feat in enumerate(self.model_features):
+            if feat.startswith('Dll_'):
+                if feat[4:] in dlls:
+                    vec[0, i] = 1.0
+            elif feat.startswith('Api_'):
+                if feat[4:] in apis:
+                    vec[0, i] = 1.0
+            else:
+                vec[0, i] = base.get(feat, 0.0)
+
+        outputs = self.sess.run(None, {self.input_name: vec})
+        
+        if len(outputs) > 1:
+            result = outputs[1]
+            if isinstance(result, list) and len(result) > 0:
+                prob_dict = result[0]
+                if hasattr(prob_dict, 'get'):
+                    return float(prob_dict.get(1, prob_dict.get('1', 0.0)))
+            elif isinstance(result, np.ndarray):
+                if result.ndim == 2 and result.shape[1] > 1:
+                    return float(result[0][1])
+        return 0.0
+
+####################################################################################################
+
+def scan_target(target, predictor):
+    files = []
+    if os.path.isfile(target):
+        files.append(target)
+    elif os.path.isdir(target):
+        for r, _, fs in os.walk(target):
+            for f in fs:
+                if os.path.splitext(f)[1].lower() in TARGET_EXTENSIONS:
+                    files.append(os.path.join(r, f))
+    
+    if not files:
+        print("[-] No valid PE files found.")
+        return
+
+    print(f"\n[*] Scanning {len(files)} files...\n")
+    print(f"{'RESULT':<10} | {'PROB':<8} | {'FILE'}")
+    print("-" * 80)
+
+    safe_count = 0
+    mal_count = 0
+    
+    for fpath in files:
+        try:
+            data = FeatureExtractor.extract(fpath)
+            if not data:
+                print(f"{'ERROR':<10} | {'----':<8} | {fpath}")
+                continue
+            
+            prob = predictor.predict(data)
+            is_malware = prob > 0.5
+            
+            label = "MALWARE" if is_malware else "SAFE"
+            if is_malware:
+                mal_count += 1
+            else:
+                safe_count += 1
+
+            print(f"{label:<10} | {prob:.4f}   | {fpath}")
+            
+        except Exception as e:
+            print(f"{'FAIL':<10} | {'----':<8} | {fpath} ({str(e)})")
+
+    print("-" * 80)
+    print(f"[*] Summary: Safe={safe_count}, Malware={mal_count}, Total={len(files)}")
+
+####################################################################################################
+
+if __name__ == "__main__":
+    print("\n-------------------------- PE Malware Predictor v4.0 --------------------------\n")
+    print(f"[*] © 2020-2026 87owo (PYAS Security)")
+    print(f"[*] Loading model features and weights...")
+
+    base_dir = os.path.dirname(sys.executable) if getattr(sys, 'frozen', False) else os.path.dirname(os.path.abspath(__file__))
+    model_path = os.path.join(base_dir, MODEL_FILE)
+    feature_path = os.path.join(base_dir, FEATURE_FILE)
+
+    try:
+        predictor = ModelPredictor(model_path, feature_path)
+    except Exception as e:
+        print(f"[-] Critical Error: {e}")
+        sys.exit(1)
+
+    if len(sys.argv) > 1:
+        for path in sys.argv[1:]:
+            target = path.strip('"').strip("'")
+            if os.path.exists(target):
+                print()
+                print("-" * 80)
+                scan_target(target, predictor)
+            else:
+                print(f"[-] Path does not exist: {target}")
+    else:
+        while True:
+            try:
+                print()
+                print("-" * 80)
+                path = input("\n[?] Enter File or Folder Path (or 'q' to exit): ").strip().strip('"').strip("'")
+                if path.lower() in ['q', 'exit']: break
+                if not os.path.exists(path):
+                    print("[-] Path does not exist.")
+                    continue
+                scan_target(path, predictor)
+            except KeyboardInterrupt:
+                break
+            except Exception as e:
+                print(f"[-] Error: {e}")

Engine/Properties/train_server.py

@@ -1,109 +1,126 @@
-import os, sys, time, sqlite3, re, json
-import pandas as pd
+import os, sys, time, json, onnxmltools
 import numpy as np
+import pandas as pd
 import lightgbm as lgb
-import onnxmltools
+import scipy.sparse as sp
 
+from collections import defaultdict
 from onnxmltools.convert.common.data_types import FloatTensorType
 from sklearn.model_selection import train_test_split
-from sklearn.metrics import classification_report, accuracy_score, roc_auc_score
+from sklearn.metrics import accuracy_score, roc_auc_score
 
 ####################################################################################################
 
-DB_PATH = "pe_features.db"
+JSONL_PATH = "pe_features.jsonl"
 MODEL_FILE = "model.txt"
 ONNX_FILE = "Pefile_General_S1.onnx"
 FEATURE_FILE = "features.json"
-TEST_SIZE = 0.1
+TEST_SIZE = 0.0001
 RANDOM_SEED = 42
 
+EXCLUDE_FEATURES = {
+    'label', 'filehash',
+}
+
 LGBM_PARAMS = {
     'objective': 'binary',
     'metric': ['binary_logloss', 'auc'],
     'boosting_type': 'gbdt',
-    'num_leaves': 512,
-    'learning_rate': 0.05,
+    'num_leaves': 256,
     'feature_fraction': 0.8,
-    'bagging_fraction': 0.8,
+    'bagging_fraction': 1.0,
     'bagging_freq': 5,
     'verbose': -1,
     'seed': RANDOM_SEED,
     'n_jobs': -1,
     'max_depth': -1,
-    'min_data_in_leaf': 10,
-    'lambda_l1': 0.05,
-    'lambda_l2': 0.05,
+    'min_data_in_leaf': 50,
 }
 
 ####################################################################################################
 
-def clean_col_name(name):
-    return re.sub(r'[^A-Za-z0-9_]+', '', name)
+def analyze_schema(jsonl_path):
+    print("[*] Stage 1: Scanning global schema...")
+    base_keys = set()
+    dll_counts = defaultdict(int)
+    api_counts = defaultdict(int)
+    num_lines = 0
 
-def get_raw_schema(db_path):
-    if not os.path.exists(db_path):
-        return None
-    conn = sqlite3.connect(db_path)
-    try:
-        cursor = conn.cursor()
-        cursor.execute("PRAGMA table_info(PeData)")
-        columns = [row[1] for row in cursor.fetchall()]
-        exclude = {'label', 'id', 'filename', 'filelength', 'rowid', 'probability', 'predictedlabel', 'score', 'filehash', 'timedatestamp'}
-        return [c for c in columns if c.lower().strip() not in exclude]
-    except Exception as e:
-        print(f"[-] Schema extraction error: {e}")
-        return None
-    finally:
-        conn.close()
+    with open(jsonl_path, 'r') as f:
+        for line in f:
+            try:
+                data = json.loads(line)
+                base_keys.update(data.get('Base', {}).keys())
+                for d in data.get('DLLs', []):
+                    dll_counts[d] += 1
+                for a in data.get('APIs', []):
+                    api_counts[a] += 1
+                num_lines += 1
+            except Exception:
+                continue
 
-####################################################################################################
-
-def load_data(db_path, raw_cols):
-    print(f"[*] Connecting to database: {db_path}")
-    conn = sqlite3.connect(db_path)
-    req_cols = list(set(raw_cols + ['Label']))
-    sql = f"SELECT {', '.join(req_cols)} FROM PeData"
+    base_schema = sorted([k for k in base_keys if k.lower().strip() not in EXCLUDE_FEATURES])
+    dll_schema = sorted([f"Dll_{k}" for k, v in dll_counts.items() if v >= 1000])
+    api_schema = sorted([f"Api_{k}" for k, v in api_counts.items() if v >= 1000])
     
-    try:
-        chunks = []
-        for chunk in pd.read_sql_query(sql, conn, chunksize=20000):
-            label_col = next((c for c in chunk.columns if c.lower().strip() == 'label'), None)
-            if not label_col:
-                print("[-] Critical Error: Label column not found.")
-                return None, None, None
-
-            cols_to_cast = [c for c in chunk.columns if c != label_col]
-            chunk[cols_to_cast] = chunk[cols_to_cast].astype(np.float32)
-            chunk[label_col] = chunk[label_col].astype(np.int8)
-            chunks.append(chunk)
-
-        if not chunks:
-            return None, None, None
-
-        df = pd.concat(chunks, ignore_index=True)
-
-        label_col = next((c for c in df.columns if c.lower().strip() == 'label'), None)
-        y = df[label_col].astype(int)
-        X = df.drop(columns=[label_col], errors='ignore')
-        
-        valid_features = [c for c in raw_cols if c in X.columns]
-        X = X[valid_features].copy()
-        
-        rename_map = {old: clean_col_name(old) for old in X.columns}
-        X = X.rename(columns=rename_map)
-        
-        if X.columns.duplicated().any():
-            print("[-] Warning: Duplicate column names detected after cleaning. Deduplicating...")
-            X = X.loc[:, ~X.columns.duplicated()]
-
-        final_features = X.columns.tolist()
-        return X, y, final_features
-    finally:
-        conn.close()
+    return base_schema, dll_schema, api_schema, num_lines
 
 ####################################################################################################
 
-def train_process(X, y):
+def load_data_efficiently(jsonl_path, base_schema, dll_schema, api_schema, num_lines):
+    print(f"[*] Stage 2: Building sparse feature matrix dynamically (Expected samples: {num_lines})...")
+    final_features = base_schema + dll_schema + api_schema
+    num_features = len(final_features)
+    feature_idx = {feat: i for i, feat in enumerate(final_features)}
+
+    rows, cols, vals = [], [], []
+    y = np.zeros(num_lines, dtype=np.int8)
+
+    with open(jsonl_path, 'r') as f:
+        row_idx = 0
+        for line in f:
+            try:
+                data = json.loads(line)
+                y[row_idx] = data.get('Label', 0)
+
+                for k, v in data.get('Base', {}).items():
+                    idx = feature_idx.get(k)
+                    if idx is not None:
+                        val = float(v)
+                        if val != 0.0:
+                            rows.append(row_idx)
+                            cols.append(idx)
+                            vals.append(val)
+
+                for d in data.get('DLLs', []):
+                    idx = feature_idx.get(f"Dll_{d}")
+                    if idx is not None:
+                        rows.append(row_idx)
+                        cols.append(idx)
+                        vals.append(1.0)
+
+                for a in data.get('APIs', []):
+                    idx = feature_idx.get(f"Api_{a}")
+                    if idx is not None:
+                        rows.append(row_idx)
+                        cols.append(idx)
+                        vals.append(1.0)
+
+                row_idx += 1
+            except Exception:
+                continue
+
+    y = y[:row_idx]
+    X = sp.csr_matrix((vals, (rows, cols)), shape=(row_idx, num_features), dtype=np.float32)
+    
+    return X, pd.Series(y), final_features
+
+####################################################################################################
+
+def _calculate_dynamic_lr(current_iter: int) -> float:
+    return max(0.01, 0.1 - (current_iter // 80) * 0.01)
+
+def train_process(X, y, feature_names):
     print(f"[*] Dataset shape: {X.shape}")
     
     X_train, X_test, y_train, y_test = train_test_split(
@@ -114,14 +131,14 @@ def train_process(X, y):
     n_neg = (y_train == 0).sum()
     
     base_weight = n_neg / n_pos if n_pos > 0 else 1.0
-    weight_ratio_target = 0.005
+    weight_ratio_target = 0.01
     final_pos_weight = base_weight * weight_ratio_target
     
-    print(f"[*] Balance Report: Safe={n_neg}, Malware={n_pos}")
-    print(f"[*] Weight Config: Base Balanced={base_weight:.4f}, Final Adjusted={final_pos_weight:.4f}")
+    print(f"[*] Sample distribution: Safe={n_neg}, Malware={n_pos}")
+    print(f"[*] Weight correction: Base={base_weight:.4f}, Final={final_pos_weight:.4f}")
     
-    train_data = lgb.Dataset(X_train, label=y_train)
-    valid_data = lgb.Dataset(X_test, label=y_test, reference=train_data)
+    train_data = lgb.Dataset(X_train, label=y_train, feature_name=feature_names)
+    valid_data = lgb.Dataset(X_test, label=y_test, reference=train_data, feature_name=feature_names)
     
     params = LGBM_PARAMS.copy()
     params['scale_pos_weight'] = final_pos_weight
@@ -133,14 +150,15 @@ def train_process(X, y):
         params,
         train_data,
         valid_sets=[valid_data],
-        num_boost_round=1000,
+        num_boost_round=500,
         callbacks=[
-            lgb.log_evaluation(period=100)
+            lgb.log_evaluation(period=50),
+            lgb.reset_parameter(learning_rate=_calculate_dynamic_lr)
         ]
     )
     
     elapsed = time.time() - start_time
-    print(f"\n[+] Training finished in {elapsed:.2f}s")
+    print(f"\n[+] Training complete, time elapsed {elapsed:.2f} seconds")
     
     return model, X_test, y_test
 
@@ -156,12 +174,10 @@ def export_onnx_model(model, feature_names):
         with open(FEATURE_FILE, 'w') as f:
             json.dump(feature_names, f)
             
-        print(f"[+] ONNX export success. Features synced to {FEATURE_FILE}")
+        print(f"[+] ONNX export successful. Feature order saved to {FEATURE_FILE}")
     except Exception as e:
         print(f"[-] ONNX export failed: {e}")
 
-####################################################################################################
-
 def evaluate_and_save(model, X_test, y_test):
     print("\n------------------- Evaluation Report -------------------\n")
     y_prob = model.predict(X_test, num_iteration=model.best_iteration)
@@ -181,14 +197,14 @@ def evaluate_and_save(model, X_test, y_test):
     detection_rate = (tp / total_malware * 100) if total_malware > 0 else 0.0
     fpr = (fp / total_safe * 100) if total_safe > 0 else 0.0
     
-    print(f"Accuracy : {acc:.4f}")
-    print(f"ROC AUC  : {auc:.4f}\n")
+    print(f"Accuracy : {acc:.6f}")
+    print(f"ROC AUC  : {auc:.6f}\n")
     
     print(f"True Positive (Class 1) : {detection_rate:.3f}% ({tp}/{total_malware})")
     print(f"False Positive (Class 0) : {fpr:.3f}% ({fp}/{total_safe})")
 
     print("\n---------------------------------------------------------\n")
-    print("[*] Top 20 Features (Importance by Gain):")
+    print("[*] Top 20 Features:")
     
     feature_names = model.feature_name()
     importance = model.feature_importance(importance_type='gain')
@@ -205,25 +221,27 @@ def evaluate_and_save(model, X_test, y_test):
 ####################################################################################################
 
 if __name__ == "__main__":
-    print("\n---------------- PE Malware Trainer v3.1 ----------------\n")
+    print("\n---------------- PE Malware Trainer v4.0 ----------------\n")
 
-    if not os.path.exists(DB_PATH):
-        print(f"[-] Error: Database {DB_PATH} not found.")
+    if not os.path.exists(JSONL_PATH):
+        print(f"[-] Error: Feature file {JSONL_PATH} not found.")
         sys.exit(1)
 
-    raw_schema = get_raw_schema(DB_PATH)
-    if not raw_schema:
-        print("[-] Error: Could not read schema.")
+    base_schema, dll_schema, api_schema, num_lines = analyze_schema(JSONL_PATH)
+    if num_lines == 0:
+        print("[-] Error: Feature file is empty.")
         sys.exit(1)
 
-    X, y, _ = load_data(DB_PATH, raw_schema)
-    if X is None:
-        sys.exit(1)
+    print(f"[*] Detected Base features: {len(base_schema)}")
+    print(f"[*] Filtered DLL features: {len(dll_schema)}")
+    print(f"[*] Filtered API features: {len(api_schema)}")
 
+    X, y, final_features = load_data_efficiently(JSONL_PATH, base_schema, dll_schema, api_schema, num_lines)
+    
     try:
-        model, X_test, y_test = train_process(X, y)
+        model, X_test, y_test = train_process(X, y, final_features)
         evaluate_and_save(model, X_test, y_test)
     except KeyboardInterrupt:
-        print("\n\n[-] Training interrupted.")
+        print("\n\n[-] Training aborted.")
     except Exception as e:
-        print(f"\n[-] Critical Error: {e}")
+        print(f"\n[-] System exception: {e}")

Engine/Properties/train_server_lfp.py

@@ -1,216 +0,0 @@
-import os, sys, time, sqlite3, re, json
-import pandas as pd
-import numpy as np
-import lightgbm as lgb
-import onnxmltools
-
-from onnxmltools.convert.common.data_types import FloatTensorType
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import classification_report, accuracy_score, roc_auc_score
-
-####################################################################################################
-
-DB_PATH = "pe_features.db"
-MODEL_FILE = "model.txt"
-ONNX_FILE = "model.onnx"
-FEATURE_FILE = "features.json"
-TEST_SIZE = 0.0001
-RANDOM_SEED = 42
-
-LGBM_PARAMS = {
-    'objective': 'binary',
-    'metric': ['binary_logloss', 'auc'],
-    'boosting_type': 'gbdt',
-    'num_leaves': 512,
-    'learning_rate': 0.05,
-    'feature_fraction': 0.8,
-    'bagging_fraction': 0.8,
-    'bagging_freq': 5,
-    'verbose': -1,
-    'seed': RANDOM_SEED,
-    'n_jobs': -1,
-    'max_depth': -1,
-    'min_data_in_leaf': 10,
-    'lambda_l1': 0.1,
-    'lambda_l2': 0.1,
-}
-
-####################################################################################################
-
-def clean_col_name(name):
-    return re.sub(r'[^A-Za-z0-9_]+', '', name)
-
-def get_raw_schema(db_path):
-    if not os.path.exists(db_path):
-        return None
-    conn = sqlite3.connect(db_path)
-    try:
-        cursor = conn.cursor()
-        cursor.execute("PRAGMA table_info(PeData)")
-        columns = [row[1] for row in cursor.fetchall()]
-        exclude = {'label', 'id', 'filename', 'filelength', 'rowid', 'probability', 'predictedlabel', 'score', 'filehash', 'timedatestamp'}
-        return [c for c in columns if c.lower().strip() not in exclude]
-    except Exception as e:
-        print(f"[-] Schema extraction error: {e}")
-        return None
-    finally:
-        conn.close()
-
-####################################################################################################
-
-def load_data(db_path, raw_cols):
-    print(f"[*] Connecting to database: {db_path}")
-    conn = sqlite3.connect(db_path)
-    req_cols = list(set(raw_cols + ['Label']))
-    sql = f"SELECT {', '.join(req_cols)} FROM PeData"
-    
-    try:
-        chunks = []
-        for chunk in pd.read_sql_query(sql, conn, chunksize=20000):
-            label_col = next((c for c in chunk.columns if c.lower().strip() == 'label'), None)
-            if not label_col:
-                print("[-] Critical Error: Label column not found.")
-                return None, None, None
-
-            cols_to_cast = [c for c in chunk.columns if c != label_col]
-            chunk[cols_to_cast] = chunk[cols_to_cast].astype(np.float32)
-            chunk[label_col] = chunk[label_col].astype(np.int8)
-            chunks.append(chunk)
-
-        if not chunks:
-            return None, None, None
-
-        df = pd.concat(chunks, ignore_index=True)
-
-        label_col = next((c for c in df.columns if c.lower().strip() == 'label'), None)
-        y = df[label_col].astype(int)
-        X = df.drop(columns=[label_col], errors='ignore')
-        
-        valid_features = [c for c in raw_cols if c in X.columns]
-        X = X[valid_features].copy()
-        
-        rename_map = {old: clean_col_name(old) for old in X.columns}
-        X = X.rename(columns=rename_map)
-        
-        if X.columns.duplicated().any():
-            print("[-] Warning: Duplicate column names detected after cleaning. Deduplicating...")
-            X = X.loc[:, ~X.columns.duplicated()]
-
-        final_features = X.columns.tolist()
-        return X, y, final_features
-    finally:
-        conn.close()
-
-####################################################################################################
-
-def train_process(X, y):
-    print(f"[*] Dataset shape: {X.shape}")
-    
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=TEST_SIZE, random_state=RANDOM_SEED, stratify=y
-    )
-    
-    n_pos = (y_train == 1).sum()
-    n_neg = (y_train == 0).sum()
-    
-    base_weight = n_neg / n_pos if n_pos > 0 else 1.0
-    weight_ratio_target = 0.001
-    final_pos_weight = base_weight * weight_ratio_target
-    
-    print(f"[*] Balance Report: Safe={n_neg}, Malware={n_pos}")
-    print(f"[*] Weight Config: Base Balanced={base_weight:.4f}, Final Adjusted={final_pos_weight:.4f}")
-    
-    train_data = lgb.Dataset(X_train, label=y_train)
-    valid_data = lgb.Dataset(X_test, label=y_test, reference=train_data)
-    
-    params = LGBM_PARAMS.copy()
-    params['scale_pos_weight'] = final_pos_weight
-
-    print("\n[*] Starting LightGBM training...")
-    start_time = time.time()
-    
-    model = lgb.train(
-        params,
-        train_data,
-        valid_sets=[valid_data],
-        num_boost_round=1000,
-        callbacks=[
-            lgb.log_evaluation(period=100)
-        ]
-    )
-    
-    elapsed = time.time() - start_time
-    print(f"\n[+] Training finished in {elapsed:.2f}s")
-    
-    return model, X_test, y_test
-
-####################################################################################################
-
-def export_onnx_model(model, feature_names):
-    print(f"[*] Exporting ONNX model to {ONNX_FILE}...")
-    try:
-        initial_type = [('float_input', FloatTensorType([None, len(feature_names)]))]
-        onnx_model = onnxmltools.convert_lightgbm(model, initial_types=initial_type)
-        onnxmltools.utils.save_model(onnx_model, ONNX_FILE)
-        
-        with open(FEATURE_FILE, 'w') as f:
-            json.dump(feature_names, f)
-            
-        print(f"[+] ONNX export success. Features synced to {FEATURE_FILE}")
-    except Exception as e:
-        print(f"[-] ONNX export failed: {e}")
-
-####################################################################################################
-
-def evaluate_and_save(model, X_test, y_test):
-    print("\n------------------- Evaluation Report -------------------\n")
-    y_prob = model.predict(X_test, num_iteration=model.best_iteration)
-    y_pred = (y_prob > 0.5).astype(int)
-    
-    acc = accuracy_score(y_test, y_pred)
-    auc = roc_auc_score(y_test, y_prob)
-    
-    print(f"Accuracy : {acc:.4f}")
-    print(f"ROC AUC  : {auc:.4f}")
-    print("\n" + classification_report(y_test, y_pred, zero_division=0))
-
-    print("---------------------------------------------------------\n")
-    print("[*] Top 20 Features (Importance by Gain):")
-    
-    feature_names = model.feature_name()
-    importance = model.feature_importance(importance_type='gain')
-    feature_imp = pd.DataFrame(sorted(zip(importance, feature_names), reverse=True), columns=['Value', 'Feature'])
-    print(feature_imp.head(20).to_string(index=False))
-    
-    print("\n---------------------------------------------------------\n")
-    
-    model.save_model(MODEL_FILE)
-    print(f"[+] Native model saved to: {os.path.abspath(MODEL_FILE)}")
-    
-    export_onnx_model(model, feature_names)
-
-####################################################################################################
-
-if __name__ == "__main__":
-    print("\n---------------- PE Malware Trainer v3.1 ----------------\n")
-
-    if not os.path.exists(DB_PATH):
-        print(f"[-] Error: Database {DB_PATH} not found.")
-        sys.exit(1)
-
-    raw_schema = get_raw_schema(DB_PATH)
-    if not raw_schema:
-        print("[-] Error: Could not read schema.")
-        sys.exit(1)
-
-    X, y, _ = load_data(DB_PATH, raw_schema)
-    if X is None:
-        sys.exit(1)
-
-    try:
-        model, X_test, y_test = train_process(X, y)
-        evaluate_and_save(model, X_test, y_test)
-    except KeyboardInterrupt:
-        print("\n\n[-] Training interrupted.")
-    except Exception as e:
-        print(f"\n[-] Critical Error: {e}")

Engine/Properties/train_user.py

@@ -1,109 +1,126 @@
-import os, sys, time, sqlite3, re, json
-import pandas as pd
+import os, sys, time, json, onnxmltools
 import numpy as np
+import pandas as pd
 import lightgbm as lgb
-import onnxmltools
+import scipy.sparse as sp
 
+from collections import defaultdict
 from onnxmltools.convert.common.data_types import FloatTensorType
 from sklearn.model_selection import train_test_split
-from sklearn.metrics import classification_report, accuracy_score, roc_auc_score
+from sklearn.metrics import accuracy_score, roc_auc_score
 
 ####################################################################################################
 
-DB_PATH = "pe_features.db"
+JSONL_PATH = "pe_features.jsonl"
 MODEL_FILE = "model.txt"
 ONNX_FILE = "Pefile_General_T1.onnx"
 FEATURE_FILE = "features.json"
-TEST_SIZE = 0.1
+TEST_SIZE = 0.0001
 RANDOM_SEED = 42
 
+EXCLUDE_FEATURES = {
+    'label', 'filehash',
+}
+
 LGBM_PARAMS = {
     'objective': 'binary',
     'metric': ['binary_logloss', 'auc'],
     'boosting_type': 'gbdt',
-    'num_leaves': 64,
-    'learning_rate': 0.05,
+    'num_leaves': 128,
     'feature_fraction': 0.8,
-    'bagging_fraction': 0.8,
+    'bagging_fraction': 1.0,
     'bagging_freq': 5,
     'verbose': -1,
     'seed': RANDOM_SEED,
     'n_jobs': -1,
     'max_depth': -1,
-    'min_data_in_leaf': 10,
-    'lambda_l1': 0.05,
-    'lambda_l2': 0.05,
+    'min_data_in_leaf': 50,
 }
 
 ####################################################################################################
 
-def clean_col_name(name):
-    return re.sub(r'[^A-Za-z0-9_]+', '', name)
+def analyze_schema(jsonl_path):
+    print("[*] Stage 1: Scanning global schema...")
+    base_keys = set()
+    dll_counts = defaultdict(int)
+    api_counts = defaultdict(int)
+    num_lines = 0
 
-def get_raw_schema(db_path):
-    if not os.path.exists(db_path):
-        return None
-    conn = sqlite3.connect(db_path)
-    try:
-        cursor = conn.cursor()
-        cursor.execute("PRAGMA table_info(PeData)")
-        columns = [row[1] for row in cursor.fetchall()]
-        exclude = {'label', 'id', 'filename', 'filelength', 'rowid', 'probability', 'predictedlabel', 'score', 'filehash', 'timedatestamp'}
-        return [c for c in columns if c.lower().strip() not in exclude]
-    except Exception as e:
-        print(f"[-] Schema extraction error: {e}")
-        return None
-    finally:
-        conn.close()
+    with open(jsonl_path, 'r') as f:
+        for line in f:
+            try:
+                data = json.loads(line)
+                base_keys.update(data.get('Base', {}).keys())
+                for d in data.get('DLLs', []):
+                    dll_counts[d] += 1
+                for a in data.get('APIs', []):
+                    api_counts[a] += 1
+                num_lines += 1
+            except Exception:
+                continue
 
-####################################################################################################
-
-def load_data(db_path, raw_cols):
-    print(f"[*] Connecting to database: {db_path}")
-    conn = sqlite3.connect(db_path)
-    req_cols = list(set(raw_cols + ['Label']))
-    sql = f"SELECT {', '.join(req_cols)} FROM PeData"
+    base_schema = sorted([k for k in base_keys if k.lower().strip() not in EXCLUDE_FEATURES])
+    dll_schema = sorted([f"Dll_{k}" for k, v in dll_counts.items() if v >= 1000])
+    api_schema = sorted([f"Api_{k}" for k, v in api_counts.items() if v >= 1000])
     
-    try:
-        chunks = []
-        for chunk in pd.read_sql_query(sql, conn, chunksize=20000):
-            label_col = next((c for c in chunk.columns if c.lower().strip() == 'label'), None)
-            if not label_col:
-                print("[-] Critical Error: Label column not found.")
-                return None, None, None
-
-            cols_to_cast = [c for c in chunk.columns if c != label_col]
-            chunk[cols_to_cast] = chunk[cols_to_cast].astype(np.float32)
-            chunk[label_col] = chunk[label_col].astype(np.int8)
-            chunks.append(chunk)
-
-        if not chunks:
-            return None, None, None
-
-        df = pd.concat(chunks, ignore_index=True)
-
-        label_col = next((c for c in df.columns if c.lower().strip() == 'label'), None)
-        y = df[label_col].astype(int)
-        X = df.drop(columns=[label_col], errors='ignore')
-        
-        valid_features = [c for c in raw_cols if c in X.columns]
-        X = X[valid_features].copy()
-        
-        rename_map = {old: clean_col_name(old) for old in X.columns}
-        X = X.rename(columns=rename_map)
-        
-        if X.columns.duplicated().any():
-            print("[-] Warning: Duplicate column names detected after cleaning. Deduplicating...")
-            X = X.loc[:, ~X.columns.duplicated()]
-
-        final_features = X.columns.tolist()
-        return X, y, final_features
-    finally:
-        conn.close()
+    return base_schema, dll_schema, api_schema, num_lines
 
 ####################################################################################################
 
-def train_process(X, y):
+def load_data_efficiently(jsonl_path, base_schema, dll_schema, api_schema, num_lines):
+    print(f"[*] Stage 2: Building sparse feature matrix dynamically (Expected samples: {num_lines})...")
+    final_features = base_schema + dll_schema + api_schema
+    num_features = len(final_features)
+    feature_idx = {feat: i for i, feat in enumerate(final_features)}
+
+    rows, cols, vals = [], [], []
+    y = np.zeros(num_lines, dtype=np.int8)
+
+    with open(jsonl_path, 'r') as f:
+        row_idx = 0
+        for line in f:
+            try:
+                data = json.loads(line)
+                y[row_idx] = data.get('Label', 0)
+
+                for k, v in data.get('Base', {}).items():
+                    idx = feature_idx.get(k)
+                    if idx is not None:
+                        val = float(v)
+                        if val != 0.0:
+                            rows.append(row_idx)
+                            cols.append(idx)
+                            vals.append(val)
+
+                for d in data.get('DLLs', []):
+                    idx = feature_idx.get(f"Dll_{d}")
+                    if idx is not None:
+                        rows.append(row_idx)
+                        cols.append(idx)
+                        vals.append(1.0)
+
+                for a in data.get('APIs', []):
+                    idx = feature_idx.get(f"Api_{a}")
+                    if idx is not None:
+                        rows.append(row_idx)
+                        cols.append(idx)
+                        vals.append(1.0)
+
+                row_idx += 1
+            except Exception:
+                continue
+
+    y = y[:row_idx]
+    X = sp.csr_matrix((vals, (rows, cols)), shape=(row_idx, num_features), dtype=np.float32)
+    
+    return X, pd.Series(y), final_features
+
+####################################################################################################
+
+def _calculate_dynamic_lr(current_iter: int) -> float:
+    return max(0.01, 0.1 - (current_iter // 80) * 0.01)
+
+def train_process(X, y, feature_names):
     print(f"[*] Dataset shape: {X.shape}")
     
     X_train, X_test, y_train, y_test = train_test_split(
@@ -117,11 +134,11 @@ def train_process(X, y):
     weight_ratio_target = 0.001
     final_pos_weight = base_weight * weight_ratio_target
     
-    print(f"[*] Balance Report: Safe={n_neg}, Malware={n_pos}")
-    print(f"[*] Weight Config: Base Balanced={base_weight:.4f}, Final Adjusted={final_pos_weight:.4f}")
+    print(f"[*] Sample distribution: Safe={n_neg}, Malware={n_pos}")
+    print(f"[*] Weight correction: Base={base_weight:.4f}, Final={final_pos_weight:.4f}")
     
-    train_data = lgb.Dataset(X_train, label=y_train)
-    valid_data = lgb.Dataset(X_test, label=y_test, reference=train_data)
+    train_data = lgb.Dataset(X_train, label=y_train, feature_name=feature_names)
+    valid_data = lgb.Dataset(X_test, label=y_test, reference=train_data, feature_name=feature_names)
     
     params = LGBM_PARAMS.copy()
     params['scale_pos_weight'] = final_pos_weight
@@ -133,14 +150,15 @@ def train_process(X, y):
         params,
         train_data,
         valid_sets=[valid_data],
-        num_boost_round=1000,
+        num_boost_round=500,
         callbacks=[
-            lgb.log_evaluation(period=100)
+            lgb.log_evaluation(period=50),
+            lgb.reset_parameter(learning_rate=_calculate_dynamic_lr)
         ]
     )
     
     elapsed = time.time() - start_time
-    print(f"\n[+] Training finished in {elapsed:.2f}s")
+    print(f"\n[+] Training complete, time elapsed {elapsed:.2f} seconds")
     
     return model, X_test, y_test
 
@@ -156,12 +174,10 @@ def export_onnx_model(model, feature_names):
         with open(FEATURE_FILE, 'w') as f:
             json.dump(feature_names, f)
             
-        print(f"[+] ONNX export success. Features synced to {FEATURE_FILE}")
+        print(f"[+] ONNX export successful. Feature order saved to {FEATURE_FILE}")
     except Exception as e:
         print(f"[-] ONNX export failed: {e}")
 
-####################################################################################################
-
 def evaluate_and_save(model, X_test, y_test):
     print("\n------------------- Evaluation Report -------------------\n")
     y_prob = model.predict(X_test, num_iteration=model.best_iteration)
@@ -181,14 +197,14 @@ def evaluate_and_save(model, X_test, y_test):
     detection_rate = (tp / total_malware * 100) if total_malware > 0 else 0.0
     fpr = (fp / total_safe * 100) if total_safe > 0 else 0.0
     
-    print(f"Accuracy : {acc:.4f}")
-    print(f"ROC AUC  : {auc:.4f}\n")
+    print(f"Accuracy : {acc:.6f}")
+    print(f"ROC AUC  : {auc:.6f}\n")
     
     print(f"True Positive (Class 1) : {detection_rate:.3f}% ({tp}/{total_malware})")
     print(f"False Positive (Class 0) : {fpr:.3f}% ({fp}/{total_safe})")
 
     print("\n---------------------------------------------------------\n")
-    print("[*] Top 20 Features (Importance by Gain):")
+    print("[*] Top 20 Features:")
     
     feature_names = model.feature_name()
     importance = model.feature_importance(importance_type='gain')
@@ -205,25 +221,27 @@ def evaluate_and_save(model, X_test, y_test):
 ####################################################################################################
 
 if __name__ == "__main__":
-    print("\n---------------- PE Malware Trainer v3.1 ----------------\n")
+    print("\n---------------- PE Malware Trainer v4.0 ----------------\n")
 
-    if not os.path.exists(DB_PATH):
-        print(f"[-] Error: Database {DB_PATH} not found.")
+    if not os.path.exists(JSONL_PATH):
+        print(f"[-] Error: Feature file {JSONL_PATH} not found.")
         sys.exit(1)
 
-    raw_schema = get_raw_schema(DB_PATH)
-    if not raw_schema:
-        print("[-] Error: Could not read schema.")
+    base_schema, dll_schema, api_schema, num_lines = analyze_schema(JSONL_PATH)
+    if num_lines == 0:
+        print("[-] Error: Feature file is empty.")
         sys.exit(1)
 
-    X, y, _ = load_data(DB_PATH, raw_schema)
-    if X is None:
-        sys.exit(1)
+    print(f"[*] Detected Base features: {len(base_schema)}")
+    print(f"[*] Filtered DLL features: {len(dll_schema)}")
+    print(f"[*] Filtered API features: {len(api_schema)}")
 
+    X, y, final_features = load_data_efficiently(JSONL_PATH, base_schema, dll_schema, api_schema, num_lines)
+    
     try:
-        model, X_test, y_test = train_process(X, y)
+        model, X_test, y_test = train_process(X, y, final_features)
         evaluate_and_save(model, X_test, y_test)
     except KeyboardInterrupt:
-        print("\n\n[-] Training interrupted.")
+        print("\n\n[-] Training aborted.")
     except Exception as e:
-        print(f"\n[-] Critical Error: {e}")
+        print(f"\n[-] System exception: {e}")

Interface/static/css/style.css

@@ -56,7 +56,7 @@ body {
 }
 
 .navigate-title {
-    font-size: 16px;
+    font-size: 17px;
     font-weight: 600;
     letter-spacing: -0.2px;
 }
@@ -797,6 +797,44 @@ body.resizing-active * {
     color: var(--text-primary);
 }
 
+.custom-context-menu {
+    position: absolute;
+    z-index: 10000;
+    background-color: var(--bg-panel);
+    border: 1px solid var(--border-color);
+    border-radius: 8px;
+    box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1);
+    padding: 4px;
+    display: none;
+    min-width: 160px;
+}
+
+.custom-context-menu.show {
+    display: block;
+}
+
+.custom-context-menu-item {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    padding: 8px 12px;
+    border-radius: 6px;
+    cursor: pointer;
+    font-size: 13px;
+    color: var(--text-primary);
+    transition: background-color 0.2s;
+}
+
+.custom-context-menu-item:hover {
+    background-color: var(--bg-hover);
+}
+
+.custom-context-menu-item svg {
+    width: 16px;
+    height: 16px;
+    color: var(--text-secondary);
+}
+
 ::-webkit-scrollbar { width: 6px; height: 6px; }
 ::-webkit-scrollbar-track { background: transparent; }
 ::-webkit-scrollbar-thumb { background: var(--border-color); border-radius: 10px; }

Interface/templates/index.html

@@ -158,7 +158,7 @@
                         </div>
                         <div class="list-item" style="cursor: pointer;" data-target="repair_window">
                             <div class="item-info">
-                                <h2 data-i18n>系統修復</h2><p data-i18n>此選項可以修復系統註冊項目</p>
+                                <h2 data-i18n>系統修復</h2><p data-i18n>此選項可以修復系統登錄檔項目</p>
                             </div>
                             <button class="icon-action-btn"><svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><polyline points="9 18 15 12 9 6"></polyline></svg></button>
                         </div>

PYAS_Engine.py

@@ -162,208 +162,6 @@ class rule_scanner:
 ####################################################################################################
 
 class pe_scanner:
-    API_CAT_MAPPING = {
-        'ProcessControl': {
-            'CreateProcessA', 'CreateProcessW', 'WinExec', 'ShellExecuteA', 'ShellExecuteW',
-            'ShellExecuteExW', 'ExitProcess', 'TerminateProcess', 'OpenProcess', 'GetExitCodeProcess',
-            'SetThreadPriority', 'GetThreadPriority', 'GetCurrentProcess', 'GetCurrentProcessId',
-            'GetModuleFileNameA', 'GetCommandLineA', 'GetModuleFileNameW', 'GetStartupInfoW'
-        },
-        'Injection': {
-            'VirtualAlloc', 'VirtualAllocEx', 'VirtualProtect', 'VirtualProtectEx', 'WriteProcessMemory', 
-            'ReadProcessMemory', 'CreateRemoteThread', 'QueueUserAPC', 'SetThreadContext', 'GetThreadContext', 
-            'Wow64SetThreadContext', 'NtUnmapViewOfSection', 'ZwUnmapViewOfSection', 'RtlCreateUserThread', 
-            'SetWindowsHookExA', 'SetWindowsHookExW', 'UnhookWindowsHookEx', 'LoadLibraryA', 'LoadLibraryW', 
-            'LoadLibraryExA', 'LoadLibraryExW', 'GetProcAddress', 'GetModuleHandleA', 'GetModuleHandleW',
-            'FreeLibrary', 'CreateFileMappingA', 'CreateFileMappingW', 'MapViewOfFile', 'UnmapViewOfSection',
-            'VirtualFree', 'VirtualQuery'
-        },
-        'Synchronization': {
-            'WaitForSingleObject', 'WaitForSingleObjectEx', 'WaitForMultipleObjects', 'WaitForMultipleObjectsEx',
-            'CreateMutexA', 'CreateMutexW', 'OpenMutexW', 'ReleaseMutex', 'CreateEventA', 'CreateEventW', 
-            'OpenEventW', 'SetEvent', 'ResetEvent', 'EnterCriticalSection', 'LeaveCriticalSection', 
-            'InitializeCriticalSection', 'DeleteCriticalSection', 'Sleep', 'SleepEx',
-            'InitializeCriticalSectionAndSpinCount', 'InterlockedDecrement', 'InterlockedIncrement', 
-            'InterlockedExchange', 'InterlockedCompareExchange', 'SetTimer', 'KillTimer'
-        },
-        'MultiThreading': {
-            'CreateThread', 'ResumeThread', 'SuspendThread', 'ExitThread', 'TerminateThread',
-            'GetCurrentThread', 'GetCurrentThreadId', 'TlsAlloc', 'TlsSetValue', 'TlsGetValue',
-            'CreateThreadpoolWork', 'SubmitThreadpoolWork', 'TlsFree'
-        },
-        'Network': {
-            'socket', 'connect', 'send', 'recv', 'bind', 'listen', 'accept', 'gethostbyname', 'getaddrinfo',
-            'WSAStartup', 'WSACleanup', 'WSAIoctl', 'WSASocketA', 'WSASocketW', 'closesocket', 'htons',
-            'InternetOpenA', 'InternetOpenW', 'InternetConnectA', 'InternetConnectW', 'InternetOpenUrlA', 
-            'InternetOpenUrlW', 'HttpOpenRequestA', 'HttpOpenRequestW', 'HttpSendRequestA', 'HttpSendRequestW',
-            'InternetReadFile', 'URLDownloadToFileA', 'URLDownloadToFileW', 'DnsQuery_A', 'DnsQuery_W'
-        },
-        'Encryption': {
-            'CryptAcquireContextA', 'CryptAcquireContextW', 'CryptCreateHash', 'CryptHashData', 
-            'CryptDeriveKey', 'CryptEncrypt', 'CryptDecrypt', 'CryptDestroyKey', 'CryptDestroyHash',
-            'CryptReleaseContext', 'CryptGenKey', 'CryptImportKey', 'CryptExportKey'
-        },
-        'DataObfuscation': {
-            'RtlDecompressBuffer', 'MultiByteToWideChar', 'WideCharToMultiByte', 'Base64Decode', 
-            'CryptDecodeObject', 'IsDBCSLeadByte', 'CharUpperA', 'CharLowerA',
-            'GetStringTypeW', 'LCMapStringW', 'IsValidCodePage', 'DecodePointer', 'EncodePointer'
-        },
-        'FileIO': {
-            'CreateFileA', 'CreateFileW', 'WriteFile', 'ReadFile', 'DeleteFileA', 'DeleteFileW',
-            'CopyFileA', 'CopyFileW', 'MoveFileA', 'MoveFileW', 'FindFirstFileA', 'FindNextFileA',
-            'GetTempPathA', 'GetTempPathW', 'GetTempFileNameA', 'GetTempFileNameW', 'SetFileAttributesA', 
-            'SetFileAttributesW', 'DeviceIoControl', 'SetFileTime', 'GetFileSize', 'GetFileSizeEx',
-            'SetFilePointer', 'FlushFileBuffers', 'ConnectNamedPipe', 'PeekNamedPipe',
-            'CloseHandle', 'GetFileType', 'SetStdHandle', 'SetFilePointerEx', 'FindClose', 
-            'SetHandleCount', 'SetEndOfFile', 'GetFullPathNameA', 'GetFileAttributesA'
-        },
-        'Registry': {
-            'RegOpenKeyExA', 'RegOpenKeyExW', 'RegSetValueExA', 'RegSetValueExW', 
-            'RegCreateKeyExA', 'RegCreateKeyExW', 'RegDeleteKeyA', 'RegDeleteKeyW',
-            'RegEnumValueA', 'RegEnumValueW', 'RegQueryValueExA', 'RegQueryValueExW',
-            'RegDeleteValueA', 'RegDeleteValueW', 'RegCloseKey'
-        },
-        'Services': {
-            'OpenSCManagerA', 'OpenSCManagerW', 'CreateServiceA', 'CreateServiceW',
-            'StartServiceA', 'StartServiceW', 'ControlService', 'DeleteService'
-        },
-        'Privileges': {
-            'AdjustTokenPrivileges', 'LookupPrivilegeValueA', 'LookupPrivilegeValueW', 
-            'OpenProcessToken', 'NetUserAdd', 'NetLocalGroupAddMembers', 'IsAdmin', 
-            'GetUserNameA', 'GetUserNameW'
-        },
-        'Native': {
-            'RtlUnwind', 'RtlVirtualUnwind', 'RtlCaptureContext', 'RtlLookupFunctionEntry',
-            'NtClose', 'NtQueryInformationProcess', 'RtlAllocateHeap', 'RtlFreeHeap',
-            'GetSystemTimeAsFileTime', 'GetLocalTime', 'GlobalMemoryStatus', 
-            'GetVersionExA', 'GetVersionExW', 'GetComputerNameA', 'GetComputerNameW',
-            'GetLastError', 'GetACP', 'RaiseException', 'SetLastError', 'GetEnvironmentStringsW', 
-            'FreeEnvironmentStringsW', 'GetLocaleInfoA', 'lstrlenA', 'GetVersion', 'GetSystemInfo', 
-            'CompareStringA'
-        },
-        'DotNet': {
-            '_CorExeMain', '_CorDllMain'
-        },
-        'AntiDebug': {
-            'IsDebuggerPresent', 'CheckRemoteDebuggerPresent', 'OutputDebugStringA', 'OutputDebugStringW',
-            'GetTickCount', 'GetTickCount64', 'QueryPerformanceCounter', 'FindWindowA', 'FindWindowW',
-            'EnumWindows', 'EnumChildWindows', 'GetWindowRect', 'GetClientRect', 'SetWindowDisplayAffinity',
-            'UnhandledExceptionFilter', 'SetUnhandledExceptionFilter', 'IsProcessorFeaturePresent', 
-            'SetErrorMode', 'GetTimeZoneInformation', 'GetDriveTypeW', 'GetDiskFreeSpaceA'
-        },
-        'Keylogging': {
-            'GetAsyncKeyState', 'GetKeyState', 'GetKeyboardState', 'MapVirtualKeyA', 'MapVirtualKeyW',
-            'ToAscii', 'ToAsciiEx', 'ToUnicode', 'ToUnicodeEx', 'GetKeyNameTextA', 'GetForegroundWindow',
-            'KeybdEvent', 'SendInput', 'MapVirtualKeyExA', 'MapVirtualKeyExW', 'CallNextHookEx'
-        },
-        'Input': {
-            'GetCursorPos', 'SetCursorPos', 'MouseEvent', 'GetDoubleClickTime', 
-            'GetCapture', 'SetCapture'
-        },
-        'ScreenCapture': {
-            'BitBlt', 'StretchBlt', 'GetDC', 'GetWindowDC', 'CreateCompatibleDC', 'CreateCompatibleBitmap',
-            'GdipSaveImageToFile', 'PrintWindow', 'GetDesktopWindow', 'CreateDCW', 'CreateDCA',
-            'SelectObject', 'DeleteDC', 'DeleteObject', 'GetDeviceCaps', 'GetSystemMetrics'
-        },
-        'Graphics': {
-            'Direct3DCreate9', 'D3D11CreateDevice'
-        },
-        'Audio': {
-            'WaveInOpen', 'WaveInClose', 'WaveInStart', 'WaveInStop'
-        },
-        'Clipboard': {
-            'OpenClipboard', 'CloseClipboard', 'GetClipboardData', 'SetClipboardData'
-        },
-        'Camera': {
-            'CapCreateCaptureWindowA', 'CapCreateCaptureWindowW'
-        },
-        'Memory': {
-            'HeapAlloc', 'HeapFree', 'HeapSize', 'HeapCreate', 'GetProcessHeap',
-            'LocalAlloc', 'LocalFree', 'GlobalAlloc', 'GlobalFree', 'GlobalUnlock',
-            'HeapDestroy', 'GlobalLock', 'SysFreeString', 'SysAllocStringLen'
-        },
-        'Resource': {
-            'LoadResource', 'SizeofResource', 'LockResource', 'FreeResource', 'FindResourceA'
-        },
-        'WindowControl': {
-            'ShowWindow', 'DestroyWindow', 'TranslateMessage', 'DispatchMessageA', 'GetWindow',
-            'PeekMessageA', 'GetWindowLongA', 'CallWindowProcA', 'SetWindowLongA', 'GetWindowTextA',
-            'ScreenToClient', 'GetActiveWindow', 'CreateWindowExA', 'DefWindowProcA', 'GetMessageA',
-            'RegisterClassA', 'UnregisterClassA', 'MessageBoxA'
-        },
-        'COM': {
-            'CoCreateInstance', 'CoUninitialize', 'CoInitialize'
-        }
-    }
-
-    TARGET_DLLS = {
-        'kernel32.dll', 'user32.dll', 'gdi32.dll', 'advapi32.dll', 'shell32.dll', 'ntdll.dll', 'hal.dll',
-        'ws2_32.dll', 'wsock32.dll', 'wininet.dll', 'winhttp.dll', 'urlmon.dll', 'crypt32.dll', 'bcrypt.dll',
-        'psapi.dll', 'dbghelp.dll', 'imagehlp.dll', 'shlwapi.dll', 'ole32.dll', 'oleaut32.dll', 'comctl32.dll',
-        'mscoree.dll', 'vbscript.dll', 'netapi32.dll', 'iphlpapi.dll', 'wtsapi32.dll', 'version.dll', 'winmm.dll'
-    }
-
-    BASE_SCHEMA = [
-        "FileEntropy", "SectionMeanEntropy", "IsExe", "IsDll", "IsDriver", "Is64Bit",
-        "Machine", "Magic", "CheckSum", "ImageBase", "SizeOfImage", "SizeOfHeaders",
-        "Characteristics", "DllCharacteristics", "Subsystem", "LoaderFlags",
-        "MajorLinkerVersion", "MinorLinkerVersion", "SizeOfCode", 
-        "SizeOfInitializedData", "SizeOfUninitializedData", "AddressOfEntryPoint",
-        "BaseOfCode", "SectionAlignment", "FileAlignment",
-        "MajorOperatingSystemVersion", "MinorOperatingSystemVersion",
-        "MajorImageVersion", "MinorImageVersion",
-        "MajorSubsystemVersion", "MinorSubsystemVersion",
-        "SizeOfStackReserve", "SizeOfStackCommit", "SizeOfHeapReserve", "SizeOfHeapCommit",
-        "NumberOfSections", "NumberOfRvaAndSizes", "PointerToSymbolTable", "NumberOfSymbols",
-        "SizeOfOptionalHeader",
-        "TextSectionMaxEntropy", "TextSectionMeanEntropy", "TextSizeRatio", 
-        "DataSectionMaxEntropy", "DataSectionMeanEntropy", "DataSizeRatio", 
-        "RsrcSectionMaxEntropy", "RsrcSectionMeanEntropy", "RsrcSizeRatio", 
-        "SectionCount", "ExecutableSections", 
-        "WritableSections", "ReadableSections", "SectionException",
-        "Char_00000020_Count", "Char_00000020_MeanEntropy",
-        "Char_00000040_Count", "Char_00000040_MeanEntropy",
-        "Char_00000080_Count", "Char_00000080_MeanEntropy",
-        "Char_02000000_Count", "Char_02000000_MeanEntropy",
-        "Char_20000000_Count", "Char_20000000_MeanEntropy",
-        "Char_40000000_Count", "Char_40000000_MeanEntropy",
-        "Char_80000000_Count", "Char_80000000_MeanEntropy",
-        "IconCount", "ApiCount", "ExportCount", "DebugCount", "ExceptionCount",
-        "ImportCount", "ImportFunctionCount",
-        "FileDescriptionLength", "FileVersionLength", "ProductNameLength", 
-        "ProductVersionLength", "CompanyNameLength", "LegalCopyrightLength", 
-        "CommentsLength", "InternalNameLength", "LegalTrademarksLength",
-        "SpecialBuildLength", "PrivateBuildLength",
-        "TrustSigned", "IsDebug", "IsPatched", "IsPrivateBuild", "IsPreRelease", 
-        "IsSpecialBuild", "IsAdmin", "IsInstall", "HasTlsCallbacks", 
-        "HasInvalidTimestamp", "HasRelocationDirectory", "HasPacked", "FileTimeException"
-    ]
-
-    CAT_SCHEMA = [f"Cat_{k}" for k in sorted(API_CAT_MAPPING.keys())]
-    DLL_SCHEMA = [f"Dll_{d.replace('.', '_')}" for d in sorted(TARGET_DLLS)]
-    
-    _ALL_APIS = {api for apis in API_CAT_MAPPING.values() for api in apis}
-    API_SCHEMA = [f"Api_{api}" for api in sorted(_ALL_APIS)]
-    SCHEMA = BASE_SCHEMA + CAT_SCHEMA + DLL_SCHEMA + API_SCHEMA
-
-    _API_TO_CATS = {}
-    for _cat, _apis in API_CAT_MAPPING.items():
-        for _api in _apis:
-            if _api not in _API_TO_CATS:
-                _API_TO_CATS[_api] = []
-            _API_TO_CATS[_api].append(_cat)
-
-    PACKERS = {
-        'upx', 'aspack', 'asprotect', 'pecompact', 'upack', 'fsg', 'mew', 
-        'mpress', 'ezip', 'pklt', 'shrink', 'petite', 'telock',
-        'themida', 'winlicense', 'tmd', 'vmp', 'enigma', 'obsidium', 
-        'pelock', 'exestealth', 'yoda', 'armadillo', 'zprotect',
-        'sforce', 'starforce', 'qihoo', 'wisevec', 'megastop',
-    }
-    INSTALLER_SIGS = [b"Nullsoft.NSIS", b"Inno Setup", b"7-Zip.7zip", b"InstallShield"]
-
-####################################################################################################
-
     def __init__(self):
         self.model = None
         self.input_name = None
@@ -387,168 +185,267 @@ class pe_scanner:
             self.model = onnxruntime.InferenceSession(model_path, providers=['CPUExecutionProvider'])
             self.input_name = self.model.get_inputs()[0].name
             feat_path = os.path.join(os.path.dirname(model_path), "features.json")
-
-            model_features = []
             if os.path.exists(feat_path):
-                with open(feat_path, 'r') as f:
-                    model_features = json.load(f)
-            else:
-                model_features = [re.sub(r'[^A-Za-z0-9_]+', '', f) for f in self.SCHEMA]
-
-            local_map = {re.sub(r'[^A-Za-z0-9_]+', '', raw_name): raw_name for raw_name in self.SCHEMA}
-            self.feature_order = [local_map.get(req_feat) for req_feat in model_features]
+                with open(feat_path, 'r', encoding='utf-8') as f:
+                    self.feature_order = json.load(f)
         except Exception:
             pass
 
-####################################################################################################
-
     def _safe_float(self, val):
         try:
             f = float(val)
-            if math.isinf(f) or math.isnan(f): return 0.0
+            if math.isinf(f) or math.isnan(f): 
+                return 0.0
             return f
         except Exception:
             return 0.0
 
-    def _safe_div(self, n, d):
-        return float(n) / d if d > 0 else 0.0
-
     def _calc_entropy(self, data):
-        if not data: return 0.0
+        if not data: 
+            return 0.0
         arr = numpy.frombuffer(data, dtype=numpy.uint8)
         counts = numpy.bincount(arr, minlength=256)
         probs = counts[counts > 0] / len(arr)
         return float(-numpy.sum(probs * numpy.log2(probs)))
 
-####################################################################################################
+    def _extract_overlay_features(self, pe, fsize):
+        overlay_offset = pe.get_overlay_data_start_offset()
+        if not overlay_offset or overlay_offset >= fsize:
+            return {"HasOverlay": 0.0, "OverlaySize": 0.0, "OverlayRatio": 0.0, "OverlayEntropy": 0.0}
+        
+        overlay_data = pe.get_overlay()
+        if not overlay_data:
+            return {"HasOverlay": 0.0, "OverlaySize": 0.0, "OverlayRatio": 0.0, "OverlayEntropy": 0.0}
+
+        sz = len(overlay_data)
+        return {
+            "HasOverlay": 1.0,
+            "OverlaySize": float(sz),
+            "OverlayRatio": float(sz) / float(fsize),
+            "OverlayEntropy": self._calc_entropy(overlay_data)
+        }
+
+    def _extract_rich_header(self, pe):
+        if not hasattr(pe, 'RICH_HEADER') or not pe.RICH_HEADER:
+            return {"HasRichHeader": 0.0, "RichHeaderCount": 0.0}
+        return {
+            "HasRichHeader": 1.0,
+            "RichHeaderCount": float(len(pe.RICH_HEADER.values) // 2) if hasattr(pe.RICH_HEADER, 'values') else 0.0
+        }
+
+    def _extract_ep_anomalies(self, pe):
+        if not hasattr(pe, 'OPTIONAL_HEADER') or not hasattr(pe, 'sections') or not pe.sections:
+            return {"EntryPointSectionIndex": -1.0, "EntryPointInExecutable": 0.0, "EntryPointInLastSection": 0.0}
+
+        ep = pe.OPTIONAL_HEADER.AddressOfEntryPoint
+        ep_section_idx = -1
+        ep_in_exec = 0.0
+        
+        for idx, sec in enumerate(pe.sections):
+            if sec.VirtualAddress <= ep < (sec.VirtualAddress + sec.Misc_VirtualSize):
+                ep_section_idx = idx
+                if sec.Characteristics & 0x20000000:
+                    ep_in_exec = 1.0
+                break
+                
+        return {
+            "EntryPointSectionIndex": float(ep_section_idx),
+            "EntryPointInExecutable": ep_in_exec,
+            "EntryPointInLastSection": 1.0 if ep_section_idx == len(pe.sections) - 1 else 0.0
+        }
+
+    def _extract_advanced_resources(self, pe):
+        res_data = {
+            "ResourceMaxEntropy": 0.0,
+            "ResourceMinEntropy": 0.0,
+            "ResourceMeanEntropy": 0.0,
+            "ResourceLangCount": 0.0,
+            "ResourceRCDataCount": 0.0
+        }
+        
+        if not hasattr(pe, 'DIRECTORY_ENTRY_RESOURCE'):
+            return res_data
+            
+        entropies = []
+        langs = set()
+        rcdata_count = 0
+        
+        for entry_type in pe.DIRECTORY_ENTRY_RESOURCE.entries:
+            if hasattr(entry_type, 'id') and entry_type.id == 10: 
+                rcdata_count += len(getattr(entry_type.directory, 'entries', []))
+                
+            if not hasattr(entry_type, 'directory'):
+                continue
+                
+            for entry_id in entry_type.directory.entries:
+                if not hasattr(entry_id, 'directory'):
+                    continue
+                    
+                for entry_lang in entry_id.directory.entries:
+                    if hasattr(entry_lang, 'id'):
+                        langs.add(entry_lang.id)
+                    if hasattr(entry_lang, 'data'):
+                        try:
+                            data = pe.get_data(entry_lang.data.struct.OffsetToData, entry_lang.data.struct.Size)
+                            entropies.append(self._calc_entropy(data))
+                        except Exception:
+                            continue
+                            
+        res_data["ResourceLangCount"] = float(len(langs))
+        res_data["ResourceRCDataCount"] = float(rcdata_count)
+        
+        if entropies:
+            res_data["ResourceMaxEntropy"] = max(entropies)
+            res_data["ResourceMinEntropy"] = min(entropies)
+            res_data["ResourceMeanEntropy"] = sum(entropies) / len(entropies)
+            
+        return res_data
+
+    def _extract_load_config(self, pe):
+        cfg = {"HasLoadConfig": 0.0, "HasCFG": 0.0, "HasSEHTable": 0.0}
+        if hasattr(pe, 'DIRECTORY_ENTRY_LOAD_CONFIG'):
+            cfg["HasLoadConfig"] = 1.0
+            struct = pe.DIRECTORY_ENTRY_LOAD_CONFIG.struct
+            if getattr(struct, 'GuardCFFunctionTable', 0) != 0:
+                cfg["HasCFG"] = 1.0
+            if getattr(struct, 'SEHandlerTable', 0) != 0:
+                cfg["HasSEHTable"] = 1.0
+        return cfg
 
     def extract_features(self, file_path):
-        fts = {k: 0.0 for k in self.SCHEMA}
         pe = None
         try:
             fsize = os.path.getsize(file_path)
-            if fsize == 0 or fsize > 512 * 1024 * 1024:
+            if fsize == 0 or fsize > 536870912:
                 return None
 
             with open(file_path, "rb") as f:
                 file_bytes = f.read()
 
+            base = {}
+            dlls = set()
+            apis = set()
             pe = pefile.PE(data=file_bytes, fast_load=True)
-            fts['TrustSigned'] = 1 if self.signer.sign_verify(file_path) else 0
+            
+            base['TrustSigned'] = 1.0 if self.signer.sign_verify(file_path) else 0.0
+            base['FileEntropy'] = self._calc_entropy(file_bytes)
+            base['FileSize'] = float(fsize)
+            
             fh = pe.FILE_HEADER
-            fts['Machine'] = fh.Machine
-            fts['NumberOfSections'] = fh.NumberOfSections
-            fts['TimeDateStamp'] = fh.TimeDateStamp
-            fts['PointerToSymbolTable'] = fh.PointerToSymbolTable
-            fts['NumberOfSymbols'] = fh.NumberOfSymbols
-            fts['SizeOfOptionalHeader'] = fh.SizeOfOptionalHeader
-            fts['Characteristics'] = fh.Characteristics
-            curr_ts = datetime.datetime.now(datetime.timezone.utc).timestamp()
-            fts['HasInvalidTimestamp'] = 1 if (fh.TimeDateStamp < 631152000 or fh.TimeDateStamp > curr_ts + 2592000) else 0
-            fts['FileTimeException'] = 1 if fh.TimeDateStamp == 0 else 0
+            base['Machine'] = getattr(fh, 'Machine', 0)
+            base['NumberOfSections'] = getattr(fh, 'NumberOfSections', 0)
+            base['TimeDateStamp'] = getattr(fh, 'TimeDateStamp', 0)
+            base['PointerToSymbolTable'] = getattr(fh, 'PointerToSymbolTable', 0)
+            base['NumberOfSymbols'] = getattr(fh, 'NumberOfSymbols', 0)
+            base['SizeOfOptionalHeader'] = getattr(fh, 'SizeOfOptionalHeader', 0)
+            base['Characteristics'] = getattr(fh, 'Characteristics', 0)
+
+            curr_ts = datetime.datetime.utcnow().timestamp()
+            base['HasInvalidTimestamp'] = 1.0 if (base['TimeDateStamp'] < 631152000 or base['TimeDateStamp'] > curr_ts + 2592000) else 0.0
+            base['FileTimeException'] = 1.0 if base['TimeDateStamp'] == 0 else 0.0
+            base['Is64Bit'] = 1.0 if base['Machine'] in (0x8664, 0xAA64, 0x0200) else 0.0
+            base['IsExe'] = 1.0 if pe.is_exe() else 0.0
+            base['IsDll'] = 1.0 if pe.is_dll() else 0.0
+
+            base['ExceptionCount'] = 0.0
 
             if hasattr(pe, 'OPTIONAL_HEADER'):
                 op = pe.OPTIONAL_HEADER
-                fts['Magic'] = getattr(op, 'Magic', 0)
-                fts['MajorLinkerVersion'] = getattr(op, 'MajorLinkerVersion', 0)
-                fts['MinorLinkerVersion'] = getattr(op, 'MinorLinkerVersion', 0)
-                fts['SizeOfCode'] = getattr(op, 'SizeOfCode', 0)
-                fts['SizeOfInitializedData'] = getattr(op, 'SizeOfInitializedData', 0)
-                fts['SizeOfUninitializedData'] = getattr(op, 'SizeOfUninitializedData', 0)
-                fts['AddressOfEntryPoint'] = getattr(op, 'AddressOfEntryPoint', 0)
-                fts['BaseOfCode'] = getattr(op, 'BaseOfCode', 0)
-                fts['ImageBase'] = getattr(op, 'ImageBase', 0)
-                fts['SectionAlignment'] = getattr(op, 'SectionAlignment', 0)
-                fts['FileAlignment'] = getattr(op, 'FileAlignment', 0)
-                fts['MajorOperatingSystemVersion'] = getattr(op, 'MajorOperatingSystemVersion', 0)
-                fts['MinorOperatingSystemVersion'] = getattr(op, 'MinorOperatingSystemVersion', 0)
-                fts['MajorImageVersion'] = getattr(op, 'MajorImageVersion', 0)
-                fts['MinorImageVersion'] = getattr(op, 'MinorImageVersion', 0)
-                fts['MajorSubsystemVersion'] = getattr(op, 'MajorSubsystemVersion', 0)
-                fts['MinorSubsystemVersion'] = getattr(op, 'MinorSubsystemVersion', 0)
-                fts['SizeOfImage'] = getattr(op, 'SizeOfImage', 0)
-                fts['SizeOfHeaders'] = getattr(op, 'SizeOfHeaders', 0)
-                fts['CheckSum'] = getattr(op, 'CheckSum', 0)
-                fts['Subsystem'] = getattr(op, 'Subsystem', 0)
-                fts['DllCharacteristics'] = getattr(op, 'DllCharacteristics', 0)
-                fts['SizeOfStackReserve'] = getattr(op, 'SizeOfStackReserve', 0)
-                fts['SizeOfStackCommit'] = getattr(op, 'SizeOfStackCommit', 0)
-                fts['SizeOfHeapReserve'] = getattr(op, 'SizeOfHeapReserve', 0)
-                fts['SizeOfHeapCommit'] = getattr(op, 'SizeOfHeapCommit', 0)
-                fts['LoaderFlags'] = getattr(op, 'LoaderFlags', 0)
-                fts['NumberOfRvaAndSizes'] = getattr(op, 'NumberOfRvaAndSizes', 0)
-                fts['Is64Bit'] = 1 if fh.Machine in (0x8664, 0xAA64, 0x0200) else 0
-                fts['IsExe'] = 1 if pe.is_exe() else 0
-                fts['IsDll'] = 1 if pe.is_dll() else 0
-                fts['IsDriver'] = 1 if fts['Subsystem'] == 1 else 0
+                fields = [
+                    'Magic', 'MajorLinkerVersion', 'MinorLinkerVersion', 'SizeOfCode',
+                    'SizeOfInitializedData', 'SizeOfUninitializedData', 'AddressOfEntryPoint',
+                    'BaseOfCode', 'ImageBase', 'SectionAlignment', 'FileAlignment',
+                    'MajorOperatingSystemVersion', 'MinorOperatingSystemVersion',
+                    'MajorImageVersion', 'MinorImageVersion', 'MajorSubsystemVersion',
+                    'MinorSubsystemVersion', 'SizeOfImage', 'SizeOfHeaders', 'CheckSum',
+                    'Subsystem', 'DllCharacteristics', 'SizeOfStackReserve', 'SizeOfStackCommit',
+                    'SizeOfHeapReserve', 'SizeOfHeapCommit', 'LoaderFlags', 'NumberOfRvaAndSizes'
+                ]
+                for f_field in fields:
+                    base[f_field] = getattr(op, f_field, 0)
+                
+                base['IsDriver'] = 1.0 if base.get('Subsystem') == 1 else 0.0
+
                 if hasattr(op, 'DATA_DIRECTORY'):
-                    reloc_idx = pefile.DIRECTORY_ENTRY.get('IMAGE_DIRECTORY_ENTRY_BASERELOC', 5)
-                    if len(op.DATA_DIRECTORY) > reloc_idx and op.DATA_DIRECTORY[reloc_idx].Size > 0:
-                        fts['HasRelocationDirectory'] = 1
+                    for i, directory in enumerate(op.DATA_DIRECTORY):
+                        base[f'DataDirectory_{i}_Size'] = directory.Size
+                        base[f'DataDirectory_{i}_VA'] = directory.VirtualAddress
+                    
+                    exc_idx = pefile.DIRECTORY_ENTRY.get('IMAGE_DIRECTORY_ENTRY_EXCEPTION', 3)
+                    if len(op.DATA_DIRECTORY) > exc_idx and op.DATA_DIRECTORY[exc_idx].Size > 0:
+                        base['ExceptionCount'] = op.DATA_DIRECTORY[exc_idx].Size // 12 if base['Machine'] in (0x8664, 0xAA64) else 0.0
 
-            try:
-                fts['FileEntropy'] = self._calc_entropy(file_bytes)
-            except Exception:
-                pass
-
-            sec_entropies = []
-            text_entropies = []
-            data_entropies = []
-            rsrc_entropies = []
             char_flags = [0x00000020, 0x00000040, 0x00000080, 0x02000000, 0x20000000, 0x40000000, 0x80000000]
+            for flag in char_flags:
+                base[f'Char_{flag:08X}_Count'] = 0.0
+                base[f'Char_{flag:08X}_MeanEntropy'] = 0.0
 
             if hasattr(pe, 'sections'):
-                fts['SectionCount'] = len(pe.sections)
+                base['SectionCount'] = len(pe.sections)
+                entropies = []
+                raw_sizes = []
+                v_sizes = []
+                exec_sec = 0
+                write_sec = 0
+                read_sec = 0
+                sec_exc = 0
+                
                 for section in pe.sections:
-                    try: 
-                        name = section.Name.decode('ascii', 'ignore').strip('\x00')
-                    except Exception: 
-                        name = ""
-                    try: 
+                    try:
                         s_data = section.get_data()
                         s_entropy = self._calc_entropy(s_data)
-                    except Exception: 
-                        s_data = b""
+                    except Exception:
                         s_entropy = 0.0
 
-                    sec_entropies.append(s_entropy)
-                    if any(p in name.lower() for p in self.PACKERS): fts['HasPacked'] = 1
-                    if section.Characteristics & 0x20000000: fts['ExecutableSections'] += 1
-                    if section.Characteristics & 0x80000000: fts['WritableSections'] += 1
-                    if section.Characteristics & 0x40000000: fts['ReadableSections'] += 1
-                    if section.SizeOfRawData + section.PointerToRawData > fsize: fts['SectionException'] = 1
+                    entropies.append(s_entropy)
+                    raw_sizes.append(section.SizeOfRawData)
+                    v_sizes.append(section.Misc_VirtualSize)
+
+                    if section.Characteristics & 0x20000000: exec_sec += 1
+                    if section.Characteristics & 0x80000000: write_sec += 1
+                    if section.Characteristics & 0x40000000: read_sec += 1
+                    if section.SizeOfRawData + section.PointerToRawData > fsize: sec_exc = 1
 
                     for flag in char_flags:
                         if section.Characteristics & flag:
-                            fts[f'Char_{flag:08X}_Count'] += 1
-                            fts[f'Char_{flag:08X}_MeanEntropy'] += s_entropy
+                            base[f'Char_{flag:08X}_Count'] += 1.0
+                            base[f'Char_{flag:08X}_MeanEntropy'] += s_entropy
 
-                    ratio = self._safe_div(section.SizeOfRawData, fsize)
-                    if name.startswith('.text'):
-                        text_entropies.append(s_entropy)
-                        fts['TextSizeRatio'] += ratio
-                    elif name.startswith('.data'):
-                        data_entropies.append(s_entropy)
-                        fts['DataSizeRatio'] += ratio
-                    elif name.startswith('.rsrc'):
-                        rsrc_entropies.append(s_entropy)
-                        fts['RsrcSizeRatio'] += ratio
-                        if b"requireAdministrator" in s_data: fts['IsAdmin'] = 1
-                        for sig in self.INSTALLER_SIGS:
-                            if sig in s_data:
-                                fts['IsInstall'] = 1
-                                break
+                base['SectionMaxEntropy'] = max(entropies) if entropies else 0.0
+                base['SectionMinEntropy'] = min(entropies) if entropies else 0.0
+                base['SectionMeanEntropy'] = sum(entropies) / len(entropies) if entropies else 0.0
+                base['SectionMaxRawSize'] = max(raw_sizes) if raw_sizes else 0.0
+                base['SectionMinRawSize'] = min(raw_sizes) if raw_sizes else 0.0
+                base['SectionMeanRawSize'] = sum(raw_sizes) / len(raw_sizes) if raw_sizes else 0.0
+                base['SectionMaxVSize'] = max(v_sizes) if v_sizes else 0.0
+                base['SectionMinVSize'] = min(v_sizes) if v_sizes else 0.0
+                base['SectionMeanVSize'] = sum(v_sizes) / len(v_sizes) if v_sizes else 0.0
+                base['ExecutableSections'] = float(exec_sec)
+                base['WritableSections'] = float(write_sec)
+                base['ReadableSections'] = float(read_sec)
+                base['SectionException'] = float(sec_exc)
 
-            fts['SectionMeanEntropy'] = self._safe_div(sum(sec_entropies), len(sec_entropies))
-            fts['TextSectionMaxEntropy'] = max(text_entropies) if text_entropies else 0.0
-            fts['TextSectionMeanEntropy'] = self._safe_div(sum(text_entropies), len(text_entropies))
-            fts['DataSectionMaxEntropy'] = max(data_entropies) if data_entropies else 0.0
-            fts['DataSectionMeanEntropy'] = self._safe_div(sum(data_entropies), len(data_entropies))
-            fts['RsrcSectionMaxEntropy'] = max(rsrc_entropies) if rsrc_entropies else 0.0
-            fts['RsrcSectionMeanEntropy'] = self._safe_div(sum(rsrc_entropies), len(rsrc_entropies))
+                for flag in char_flags:
+                    if base[f'Char_{flag:08X}_Count'] > 0:
+                        base[f'Char_{flag:08X}_MeanEntropy'] = base[f'Char_{flag:08X}_MeanEntropy'] / base[f'Char_{flag:08X}_Count']
 
-            for flag in char_flags:
-                fts[f'Char_{flag:08X}_MeanEntropy'] = self._safe_div(fts[f'Char_{flag:08X}_MeanEntropy'], fts[f'Char_{flag:08X}_Count'])
+            string_keys = ['FileDescription', 'FileVersion', 'ProductName', 'ProductVersion', 'CompanyName', 'LegalCopyright', 'Comments', 'InternalName', 'LegalTrademarks', 'SpecialBuild', 'PrivateBuild']
+            for key in string_keys: 
+                base[f'{key}Length'] = 0.0
+                
+            if hasattr(pe, 'FileInfo'):
+                for fileinfo_list in pe.FileInfo:
+                    for fileinfo in fileinfo_list:
+                        if getattr(fileinfo, 'name', '') in ('StringFileInfo', b'StringFileInfo'):
+                            for st in getattr(fileinfo, 'StringTable', []):
+                                for key, val in st.entries.items():
+                                    try:
+                                        k = key.decode('utf-8', 'ignore') if isinstance(key, bytes) else str(key)
+                                        if k in string_keys:
+                                            v = val.decode('utf-8', 'ignore') if isinstance(val, bytes) else str(val)
+                                            base[f'{k}Length'] = float(len(v))
+                                    except Exception: 
+                                        continue
 
             try:
                 pe.parse_data_directories(directories=[
@@ -563,110 +460,96 @@ class pe_scanner:
 
             if hasattr(pe, 'DIRECTORY_ENTRY_TLS') and hasattr(pe.DIRECTORY_ENTRY_TLS, 'struct'):
                 if getattr(pe.DIRECTORY_ENTRY_TLS.struct, 'AddressOfCallBacks', 0) != 0:
-                    fts['HasTlsCallbacks'] = 1
-
+                    base['HasTlsCallbacks'] = 1.0
+            
             if hasattr(pe, 'VS_FIXEDFILEINFO') and len(pe.VS_FIXEDFILEINFO) > 0:
                 flags = getattr(pe.VS_FIXEDFILEINFO[0], 'FileFlags', 0)
-                fts['IsDebug'] = 1 if flags & 0x1 else 0
-                fts['IsPreRelease'] = 1 if flags & 0x2 else 0
-                fts['IsPatched'] = 1 if flags & 0x4 else 0
-                fts['IsPrivateBuild'] = 1 if flags & 0x8 else 0
-                fts['IsSpecialBuild'] = 1 if flags & 0x20 else 0
-
-            if hasattr(pe, 'FileInfo'):
-                for fileinfo_list in pe.FileInfo:
-                    for fileinfo in fileinfo_list:
-                        if getattr(fileinfo, 'name', '') in ('StringFileInfo', b'StringFileInfo'):
-                            for st in getattr(fileinfo, 'StringTable', []):
-                                for key, val in st.entries.items():
-                                    try:
-                                        k = key.decode('utf-8', 'ignore') if isinstance(key, bytes) else str(key)
-                                        v = val.decode('utf-8', 'ignore') if isinstance(val, bytes) else str(val)
-                                        length = len(v)
-                                        if k == 'FileDescription': fts['FileDescriptionLength'] = length
-                                        elif k == 'FileVersion': fts['FileVersionLength'] = length
-                                        elif k == 'ProductName': fts['ProductNameLength'] = length
-                                        elif k == 'ProductVersion': fts['ProductVersionLength'] = length
-                                        elif k == 'CompanyName': fts['CompanyNameLength'] = length
-                                        elif k == 'LegalCopyright': fts['LegalCopyrightLength'] = length
-                                        elif k == 'Comments': fts['CommentsLength'] = length
-                                        elif k == 'InternalName': fts['InternalNameLength'] = length
-                                        elif k == 'LegalTrademarks': fts['LegalTrademarksLength'] = length
-                                        elif k == 'SpecialBuild': fts['SpecialBuildLength'] = length
-                                        elif k == 'PrivateBuild': fts['PrivateBuildLength'] = length
-                                    except Exception:
-                                        continue
+                base['IsDebug'] = 1.0 if flags & 0x1 else 0.0
+                base['IsPreRelease'] = 1.0 if flags & 0x2 else 0.0
+                base['IsPatched'] = 1.0 if flags & 0x4 else 0.0
+                base['IsPrivateBuild'] = 1.0 if flags & 0x8 else 0.0
+                base['IsSpecialBuild'] = 1.0 if flags & 0x20 else 0.0
 
             if hasattr(pe, 'DIRECTORY_ENTRY_IMPORT'):
-                fts['ImportCount'] = len(pe.DIRECTORY_ENTRY_IMPORT)
+                base['ImportCount'] = float(len(pe.DIRECTORY_ENTRY_IMPORT))
+                func_count = 0
                 for entry in pe.DIRECTORY_ENTRY_IMPORT:
                     if getattr(entry, 'dll', None):
                         try:
-                            dll_name = entry.dll.decode('ascii', 'ignore').lower()
-                            if dll_name in self.TARGET_DLLS: 
-                                fts[f"Dll_{dll_name.replace('.', '_')}"] = 1.0
-                        except Exception: 
+                            dlls.add(entry.dll.decode('ascii', 'ignore').lower())
+                        except Exception:
                             pass
-
-                    imports = getattr(entry, 'imports', [])
-                    for imp in imports:
-                        fts['ImportFunctionCount'] += 1
-                        if not getattr(imp, 'name', None): continue
-                        try:
-                            func_name = imp.name.decode('ascii', 'ignore')
-                            if func_name in self._ALL_APIS:
-                                fts[f'Api_{func_name}'] += 1
-                                fts['ApiCount'] += 1
-                            for cat in self._API_TO_CATS.get(func_name, []):
-                                fts[f'Cat_{cat}'] += 1
-                        except Exception: 
-                            continue
+                    for imp in getattr(entry, 'imports', []):
+                        func_count += 1
+                        if getattr(imp, 'name', None):
+                            try:
+                                apis.add(imp.name.decode('ascii', 'ignore'))
+                            except Exception:
+                                pass
+                base['ImportFunctionCount'] = float(func_count)
+            else:
+                base['ImportCount'] = 0.0
+                base['ImportFunctionCount'] = 0.0
 
             if hasattr(pe, 'DIRECTORY_ENTRY_EXPORT') and hasattr(pe.DIRECTORY_ENTRY_EXPORT, 'symbols'):
-                fts['ExportCount'] = len(pe.DIRECTORY_ENTRY_EXPORT.symbols)
-            
+                base['ExportCount'] = float(len(pe.DIRECTORY_ENTRY_EXPORT.symbols))
+            else:
+                base['ExportCount'] = 0.0
+
             if hasattr(pe, 'DIRECTORY_ENTRY_RESOURCE'):
+                icon_count = 0
                 for entry in pe.DIRECTORY_ENTRY_RESOURCE.entries:
                     if getattr(entry, 'id', None) == 3 and hasattr(entry, 'directory'):
-                        fts['IconCount'] += len(getattr(entry.directory, 'entries', []))
-                        
-            if hasattr(pe, 'OPTIONAL_HEADER') and hasattr(pe.OPTIONAL_HEADER, 'DATA_DIRECTORY') and len(pe.OPTIONAL_HEADER.DATA_DIRECTORY) > 3:
-                exc_dir = pe.OPTIONAL_HEADER.DATA_DIRECTORY[3]
-                if exc_dir.Size > 0:
-                    fts['ExceptionCount'] = exc_dir.Size // 12 if fts['Machine'] in (0x8664, 0xAA64) else 0
-                
-            if hasattr(pe, 'DIRECTORY_ENTRY_DEBUG'): 
-                fts['DebugCount'] = len(pe.DIRECTORY_ENTRY_DEBUG)
+                        icon_count += len(getattr(entry.directory, 'entries', []))
+                base['IconCount'] = float(icon_count)
+            else:
+                base['IconCount'] = 0.0
 
-            for k in fts: 
-                fts[k] = self._safe_float(fts[k])
-                
-            return fts
+            if hasattr(pe, 'DIRECTORY_ENTRY_DEBUG'):
+                base['DebugCount'] = float(len(pe.DIRECTORY_ENTRY_DEBUG))
+            else:
+                base['DebugCount'] = 0.0
+
+            base.update(self._extract_overlay_features(pe, fsize))
+            base.update(self._extract_rich_header(pe))
+            base.update(self._extract_ep_anomalies(pe))
+            base.update(self._extract_advanced_resources(pe))
+            base.update(self._extract_load_config(pe))
+
+            for k in base:
+                base[k] = self._safe_float(base[k])
+
+            return {"Base": base, "DLLs": list(dlls), "APIs": list(apis)}
 
         except Exception:
             return None
         finally:
-            if pe: 
+            if pe:
                 pe.close()
 
-####################################################################################################
-
     def pe_scan(self, file_path, enhanced_mode=False):
-        if not self.model:
+        if not self.model or not self.feature_order:
             return False, False
         try:
-            data = self.extract_features(file_path)
-            if not data:
+            raw_data = self.extract_features(file_path)
+            if not raw_data:
                 return False, False
 
-            vec_data = []
-            for key in self.feature_order:
-                if key:
-                    vec_data.append(data.get(key, 0.0))
+            vec = numpy.zeros((1, len(self.feature_order)), dtype=numpy.float32)
+            base = raw_data.get('Base', {})
+            dlls = set(raw_data.get('DLLs', []))
+            apis = set(raw_data.get('APIs', []))
+
+            for i, feat in enumerate(self.feature_order):
+                if feat.startswith('Dll_'):
+                    if feat[4:] in dlls:
+                        vec[0, i] = 1.0
+                elif feat.startswith('Api_'):
+                    if feat[4:] in apis:
+                        vec[0, i] = 1.0
                 else:
-                    vec_data.append(0.0)
+                    vec[0, i] = base.get(feat, 0.0)
 
-            vec = numpy.array(vec_data, dtype=numpy.float32).reshape(1, -1)
             outputs = self.model.run(None, {self.input_name: vec})
             result = outputs[1]
             prob = 0.0
@@ -675,7 +558,6 @@ class pe_scanner:
                 prob_dict = result[0]
                 if hasattr(prob_dict, 'get'):
                     prob = float(prob_dict.get(1, prob_dict.get('1', 0.0)))
-
             elif isinstance(result, numpy.ndarray):
                 if result.ndim == 2 and result.shape[1] > 1:
                     prob = float(result[0][1])

PYAS_Version.py

@@ -2,7 +2,7 @@ import pyinstaller_versionfile
 
 pyinstaller_versionfile.create_versionfile(
 output_file="versionfile.txt",
-version='3.5.3.0',
+version='3.5.5.0',
 company_name="PYAS Security",
 file_description="PYAS Security Antivirus",
 internal_name="PYAS",

Plugins/Rules/Rules_Driver_P1.json

@@ -2,7 +2,6 @@
   "Rule_Registry_BlockList": [
     "\\REGISTRY\\MACHINE\\BCD00000000",
     "\\REGISTRY\\MACHINE\\BCD00000000\\*",
-    "*\\Image File Execution Options\\*",
     
     "*\\Classes\\.exe",
     "*\\Classes\\.bat",
@@ -78,12 +77,10 @@
     "*\\FirmwareBootDevice",
     "*\\BootDriverFlags",
     "*\\SystemStartOptions",
-    "*\\CrashDumpEnabled",
     "*\\DisableAutomaticRestartOnFailure",
     "*\\SystemBiosVersion",
     "*\\NoTheme",
     "*\\SystemSetupInProgress",
-    "*\\CmdLine",
     "*\\SetupType",
     "*\\AutoReboot",
     "*\\Userinit",
@@ -106,27 +103,38 @@
     
     "\\Device\\HarddiskVolume*\\ProgramData\\Microsoft\\Windows Defender\\*",
     "\\Device\\HarddiskVolume*\\ProgramData\\Microsoft\\Windows Defender Advanced Threat Protection\\*",
+    "*\\Sources\\SetupHost.exe",
+    "*\\Work\\*\\DismHost.exe",
     
     "*\\Google\\Chrome\\Application\\chrome.exe",
     "*\\Microsoft\\Edge\\Application\\msedge.exe",
     "*\\Mozilla Firefox\\firefox.exe",
+    "*\\Thorium\\Application\\thorium.exe",
     
     "*\\Steam\\steam.exe",
     "*\\steam\\*\\steam.exe",
     "*\\Battle.net\\*\\Battle.net.exe",
     "*\\Epic Games\\Launcher\\Portal\\Binaries\\*\\EpicGamesLauncher.exe",
     
+    "*\\resources\\bin\\SDK\\DownloadSDKServer.exe",
     "*\\ThunderEv.exe",
     "*\\ThunderStart.exe",
-    "*\\resources\\bin\\SDK\\DownloadSDKServer.exe",
     "*\\KuGou.exe",
     "*\\XLGame.exe",
     "*\\XLLiveUD.exe",
-    "*\\PC4399_WPFLauncher.exe",
-    "*\\bin\\APlayer.exe",
+    
     "*\\hrkill-*.exe",
     "*\\bin\\HipsDaemon.exe",
     "*\\360Safe.exe",
+    "*\\bilibili\\bilibili.exe",
+    
+    "*\\Kingsoft\\WPS Office\\ksolaunch.exe",
+    "*\\Kingsoft\\WPS Office\\*\\wps.exe",
+    
+    "*\\PC4399_WPFLauncher.exe",
+    "*\\bin\\APlayer.exe",
+    "*\\Neverness To Everness\\NTELauncher.exe",
+    "*\\Application\\AndrowsLauncher.exe",
   ],
   "Rule_Process_ExploitableBlacklist": [
     "*\\cmd.exe",

README.md

@@ -26,6 +26,7 @@ pip install pandas
 pip install scikit-learn
 pip install lightgbm
 pip install onnxmltools
+pip install orjson
 ```
 
 ## File Information