1102 lines
43 KiB
Python
1102 lines
43 KiB
Python
import re, os, sys, math, time, zlib, datetime, hashlib
|
|
import ctypes, ctypes.wintypes, pefile, multiprocessing
|
|
import numpy as np
|
|
|
|
####################################################################################################
|
|
|
|
try:
|
|
import orjson
|
|
JSON_DUMPS = lambda x: orjson.dumps(x).decode('utf-8')
|
|
JSON_LOADS = orjson.loads
|
|
HAS_ORJSON = True
|
|
|
|
except ImportError:
|
|
import json
|
|
JSON_DUMPS = json.dumps
|
|
JSON_LOADS = json.loads
|
|
HAS_ORJSON = False
|
|
|
|
####################################################################################################
|
|
|
|
JSONL_PATH = "pe_features.jsonl"
|
|
BATCH_SIZE = 1000
|
|
MAX_FILE_SIZE = 4 * 1024 * 1024 * 1024
|
|
MAX_WORKERS = os.cpu_count() - 2
|
|
|
|
####################################################################################################
|
|
|
|
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))
|
|
|
|
####################################################################################################
|
|
|
|
def verify_signature(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
|
|
|
|
abs_path = os.path.abspath(file_path)
|
|
|
|
fi = WINTRUST_FILE_INFO()
|
|
fi.cbStruct = ctypes.sizeof(WINTRUST_FILE_INFO)
|
|
fi.pcwszFilePath = abs_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
|
|
|
|
####################################################################################################
|
|
|
|
def _entropy_from_counts(counts, size):
|
|
if size <= 0:
|
|
return 0.0
|
|
nonzero = counts[counts > 0]
|
|
return float(np.log2(size) - np.sum(nonzero * np.log2(nonzero)) / size)
|
|
|
|
|
|
def _bounded_entropy(data, batch_size=1048576):
|
|
size = len(data)
|
|
if size == 0:
|
|
return 0.0
|
|
counts = np.zeros(256, dtype=np.int64)
|
|
view = memoryview(data)
|
|
try:
|
|
for start in range(0, size, batch_size):
|
|
chunk = np.frombuffer(
|
|
view[start:min(start + batch_size, size)], dtype=np.uint8
|
|
)
|
|
counts += np.bincount(chunk, minlength=256)
|
|
finally:
|
|
view.release()
|
|
return _entropy_from_counts(counts, size)
|
|
|
|
|
|
def _accumulate_string_chunk(chunk, array, state, pattern):
|
|
separators = (array < 0x20) | (array > 0x7E)
|
|
if not separators.any():
|
|
state["pending_counts"] += np.bincount(array, minlength=256)
|
|
state["pending_length"] += len(array)
|
|
return
|
|
|
|
first_separator = int(np.argmax(separators))
|
|
last_separator = len(separators) - 1 - int(np.argmax(separators[::-1]))
|
|
if first_separator:
|
|
state["pending_counts"] += np.bincount(
|
|
array[:first_separator], minlength=256
|
|
)
|
|
state["pending_length"] += first_separator
|
|
if state["pending_length"] >= 5:
|
|
state["count"] += 1
|
|
state["total_length"] += state["pending_length"]
|
|
state["counts"] += state["pending_counts"]
|
|
state["pending_length"] = 0
|
|
state["pending_counts"].fill(0)
|
|
|
|
middle_start = first_separator + 1
|
|
middle_end = last_separator
|
|
if middle_end > middle_start:
|
|
matches = pattern.findall(chunk[middle_start:middle_end])
|
|
if matches:
|
|
combined = b"".join(matches)
|
|
state["count"] += len(matches)
|
|
state["total_length"] += len(combined)
|
|
state["counts"] += np.bincount(
|
|
np.frombuffer(combined, dtype=np.uint8), minlength=256
|
|
)
|
|
|
|
trailing_start = last_separator + 1
|
|
if trailing_start < len(array):
|
|
trailing = array[trailing_start:]
|
|
state["pending_counts"] += np.bincount(trailing, minlength=256)
|
|
state["pending_length"] = len(trailing)
|
|
|
|
|
|
def _accumulate_entropy_windows(data, entropy_histogram, c_log_c_table):
|
|
block_count = len(data) // 1024
|
|
if block_count < 2:
|
|
return data
|
|
|
|
complete_size = block_count * 1024
|
|
blocks = np.frombuffer(
|
|
data, dtype=np.uint8, count=complete_size
|
|
).reshape(block_count, 1024)
|
|
encoded = blocks.astype(np.int32)
|
|
encoded += np.arange(block_count, dtype=np.int32)[:, None] * 256
|
|
block_counts = np.bincount(
|
|
encoded.ravel(), minlength=block_count * 256
|
|
).reshape(block_count, 256)
|
|
window_counts = block_counts[:-1] + block_counts[1:]
|
|
sum_c_log_c = np.sum(c_log_c_table[window_counts], axis=1)
|
|
entropies = 11.0 - sum_c_log_c / 2048.0
|
|
entropy_bins = (entropies * 2.0).astype(np.int32)
|
|
np.clip(entropy_bins, 0, 15, out=entropy_bins)
|
|
byte_bins = window_counts.reshape(block_count - 1, 16, 16).sum(axis=2)
|
|
flat_indices = (entropy_bins[:, None] * 16 + np.arange(16)).ravel()
|
|
np.add.at(entropy_histogram, flat_indices, byte_bins.ravel())
|
|
return data[(block_count - 1) * 1024:]
|
|
|
|
|
|
def _collect_resource_ranges(pe, file_size):
|
|
ranges = []
|
|
if not hasattr(pe, "DIRECTORY_ENTRY_RESOURCE"):
|
|
return ranges
|
|
for entry_type in pe.DIRECTORY_ENTRY_RESOURCE.entries:
|
|
for entry_id in getattr(
|
|
getattr(entry_type, "directory", None), "entries", []
|
|
):
|
|
for entry_lang in getattr(
|
|
getattr(entry_id, "directory", None), "entries", []
|
|
):
|
|
if not hasattr(entry_lang, "data"):
|
|
continue
|
|
try:
|
|
struct = entry_lang.data.struct
|
|
offset = int(pe.get_offset_from_rva(int(struct.OffsetToData)))
|
|
size = int(struct.Size)
|
|
start = max(0, offset)
|
|
end = min(file_size, start + max(0, size))
|
|
ranges.append((start, max(start, end)))
|
|
except Exception:
|
|
ranges.append((0, 0))
|
|
return ranges
|
|
|
|
|
|
def _extract_stream_features(file_path, file_size, ranges, extractor):
|
|
normalized = []
|
|
for start, end in ranges:
|
|
start = max(0, min(file_size, int(start)))
|
|
end = max(start, min(file_size, int(end)))
|
|
normalized.append((start, end))
|
|
|
|
byte_counts = np.zeros(256, dtype=np.int64)
|
|
range_counts = [np.zeros(256, dtype=np.int64) for _ in normalized]
|
|
entropy_histogram = np.zeros(256, dtype=np.float64)
|
|
string_state = {
|
|
"count": 0,
|
|
"total_length": 0,
|
|
"counts": np.zeros(256, dtype=np.int64),
|
|
"pending_length": 0,
|
|
"pending_counts": np.zeros(256, dtype=np.int64),
|
|
}
|
|
histogram_tail = b""
|
|
position = 0
|
|
|
|
with open(file_path, "rb") as source:
|
|
while True:
|
|
chunk = source.read(4194304)
|
|
if not chunk:
|
|
break
|
|
array = np.frombuffer(chunk, dtype=np.uint8)
|
|
_accumulate_string_chunk(
|
|
chunk, array, string_state, extractor._STRING_PATTERN
|
|
)
|
|
histogram_tail = _accumulate_entropy_windows(
|
|
histogram_tail + chunk,
|
|
entropy_histogram,
|
|
extractor._C_LOG_C_TABLE,
|
|
)
|
|
|
|
chunk_end = position + len(chunk)
|
|
boundaries = {0, len(chunk)}
|
|
for start, end in normalized:
|
|
if position < start < chunk_end:
|
|
boundaries.add(start - position)
|
|
if position < end < chunk_end:
|
|
boundaries.add(end - position)
|
|
|
|
ordered = sorted(boundaries)
|
|
for index in range(len(ordered) - 1):
|
|
local_start = ordered[index]
|
|
local_end = ordered[index + 1]
|
|
if local_end <= local_start:
|
|
continue
|
|
counts = np.bincount(
|
|
array[local_start:local_end], minlength=256
|
|
)
|
|
byte_counts += counts
|
|
absolute_start = position + local_start
|
|
absolute_end = position + local_end
|
|
for range_index, (start, end) in enumerate(normalized):
|
|
if start <= absolute_start and absolute_end <= end:
|
|
range_counts[range_index] += counts
|
|
position = chunk_end
|
|
|
|
if string_state["pending_length"] >= 5:
|
|
string_state["count"] += 1
|
|
string_state["total_length"] += string_state["pending_length"]
|
|
string_state["counts"] += string_state["pending_counts"]
|
|
|
|
string_count = string_state["count"]
|
|
total_string_length = string_state["total_length"]
|
|
result = {
|
|
"StringCount": float(string_count),
|
|
"StringMeanLength": (
|
|
float(total_string_length) / string_count if string_count else 0.0
|
|
),
|
|
"StringEntropy": _entropy_from_counts(
|
|
string_state["counts"], total_string_length
|
|
),
|
|
}
|
|
result.update(dict.fromkeys(extractor._STRING_KEYS, 0.0))
|
|
if total_string_length:
|
|
valid_counts = string_state["counts"][0x20:0x7F]
|
|
result.update(dict(zip(
|
|
extractor._STRING_KEYS,
|
|
valid_counts.astype(np.float64) / total_string_length,
|
|
)))
|
|
|
|
result["FileEntropy"] = _entropy_from_counts(byte_counts, file_size)
|
|
result.update(dict(zip(
|
|
extractor._BYTE_HIST_KEYS,
|
|
byte_counts.astype(np.float64) / file_size,
|
|
)))
|
|
entropy_sum = np.sum(entropy_histogram)
|
|
if entropy_sum:
|
|
entropy_histogram /= entropy_sum
|
|
result.update(dict(zip(extractor._BYTE_ENT_KEYS, entropy_histogram)))
|
|
|
|
range_entropies = [
|
|
_entropy_from_counts(counts, end - start)
|
|
for counts, (start, end) in zip(range_counts, normalized)
|
|
]
|
|
return result, range_entropies
|
|
|
|
|
|
class FeatureExtractor:
|
|
_STRING_PATTERN = re.compile(b'[\x20-\x7E]{5,}')
|
|
_STRING_FAST_PATH_BYTES = 4194304
|
|
_STRING_BATCH_BYTES = 4194304
|
|
_HISTOGRAM_BATCH_WINDOWS = 1024
|
|
|
|
_BYTE_HIST_KEYS = [f'ByteHist_{i:02X}' for i in range(256)]
|
|
_BYTE_ENT_KEYS = [f'ByteEnt_{i:02X}' for i in range(256)]
|
|
_STRING_KEYS = [f'StringHist_{i:02d}' for i in range(95)]
|
|
_SECTION_HASH_KEYS = [f'SectionHash_{i:02d}' for i in range(50)]
|
|
_CHAR_FLAGS = [0x00000020, 0x00000040, 0x00000080, 0x02000000, 0x20000000, 0x40000000, 0x80000000]
|
|
_CHAR_COUNT_KEYS = {flag: f'Char_{flag:08X}_Count' for flag in _CHAR_FLAGS}
|
|
_CHAR_ENT_KEYS = {flag: f'Char_{flag:08X}_MeanEntropy' for flag in _CHAR_FLAGS}
|
|
|
|
_C_LOG_C_TABLE = np.zeros(2049, dtype=np.float64)
|
|
_C_LOG_C_TABLE[1:] = np.arange(1, 2049) * np.log2(np.arange(1, 2049))
|
|
|
|
_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'
|
|
]
|
|
|
|
_SECTION_DEFAULTS = {
|
|
'SectionCount': 0.0,
|
|
'SectionMaxEntropy': 0.0,
|
|
'SectionMinEntropy': 0.0,
|
|
'SectionMeanEntropy': 0.0,
|
|
'SectionMaxRawSize': 0.0,
|
|
'SectionMinRawSize': 0.0,
|
|
'SectionMeanRawSize': 0.0,
|
|
'SectionMaxVSize': 0.0,
|
|
'SectionMinVSize': 0.0,
|
|
'SectionMeanVSize': 0.0,
|
|
'ExecutableSections': 0.0,
|
|
'WritableSections': 0.0,
|
|
'ReadableSections': 0.0,
|
|
'SectionException': 0.0
|
|
}
|
|
|
|
_CONDITIONAL_DEFAULTS = {
|
|
'IsDriver': 0.0,
|
|
'HasTlsCallbacks': 0.0,
|
|
'IsDebug': 0.0,
|
|
'IsPreRelease': 0.0,
|
|
'IsPatched': 0.0,
|
|
'IsPrivateBuild': 0.0,
|
|
'IsSpecialBuild': 0.0,
|
|
'ImportCount': 0.0,
|
|
'ImportFunctionCount': 0.0,
|
|
'ExportCount': 0.0,
|
|
'IconCount': 0.0,
|
|
'DebugCount': 0.0
|
|
}
|
|
|
|
@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
|
|
|
|
@classmethod
|
|
def _base_defaults(cls):
|
|
base = dict.fromkeys(cls._OPTIONAL_HEADER_FIELDS, 0.0)
|
|
base.update(cls._SECTION_DEFAULTS)
|
|
base.update(cls._CONDITIONAL_DEFAULTS)
|
|
|
|
for i in range(16):
|
|
base[f'DataDirectory_{i}_Size'] = 0.0
|
|
base[f'DataDirectory_{i}_VA'] = 0.0
|
|
|
|
return base
|
|
|
|
@staticmethod
|
|
def _calc_entropy(data):
|
|
return _bounded_entropy(data)
|
|
|
|
@classmethod
|
|
def _extract_strings(cls, file_bytes):
|
|
res = {"StringCount": 0.0, "StringMeanLength": 0.0, "StringEntropy": 0.0}
|
|
res.update(dict.fromkeys(cls._STRING_KEYS, 0.0))
|
|
|
|
if len(file_bytes) <= cls._STRING_FAST_PATH_BYTES:
|
|
matches = cls._STRING_PATTERN.findall(file_bytes)
|
|
if not matches:
|
|
return res
|
|
|
|
combined_data = b''.join(matches)
|
|
count = len(matches)
|
|
total_len = len(combined_data)
|
|
global_counts = np.bincount(np.frombuffer(combined_data, dtype=np.uint8), minlength=256)
|
|
else:
|
|
count = 0
|
|
total_len = 0
|
|
global_counts = np.zeros(256, dtype=np.int64)
|
|
mv = memoryview(file_bytes)
|
|
pos = 0
|
|
size = len(file_bytes)
|
|
|
|
while pos < size:
|
|
chunk_end = min(pos + cls._STRING_BATCH_BYTES, size)
|
|
chunk_arr = np.frombuffer(mv[pos:chunk_end], dtype=np.uint8)
|
|
separators = (chunk_arr < 0x20) | (chunk_arr > 0x7E)
|
|
|
|
if separators.any():
|
|
last_separator = len(separators) - 1 - int(np.argmax(separators[::-1]))
|
|
segment_end = pos + last_separator + 1
|
|
matches = cls._STRING_PATTERN.findall(mv[pos:segment_end])
|
|
|
|
if matches:
|
|
combined_data = b''.join(matches)
|
|
count += len(matches)
|
|
total_len += len(combined_data)
|
|
global_counts += np.bincount(np.frombuffer(combined_data, dtype=np.uint8), minlength=256)
|
|
|
|
pos = segment_end
|
|
continue
|
|
|
|
pending_len = 0
|
|
pending_counts = np.zeros(256, dtype=np.int64)
|
|
|
|
while pos < size:
|
|
chunk_end = min(pos + cls._STRING_BATCH_BYTES, size)
|
|
chunk_arr = np.frombuffer(mv[pos:chunk_end], dtype=np.uint8)
|
|
separators = (chunk_arr < 0x20) | (chunk_arr > 0x7E)
|
|
|
|
if separators.any():
|
|
first_separator = int(np.argmax(separators))
|
|
if first_separator:
|
|
pending_counts += np.bincount(chunk_arr[:first_separator], minlength=256)
|
|
pending_len += first_separator
|
|
pos += first_separator + 1
|
|
break
|
|
|
|
pending_counts += np.bincount(chunk_arr, minlength=256)
|
|
pending_len += len(chunk_arr)
|
|
pos = chunk_end
|
|
|
|
if pending_len >= 5:
|
|
count += 1
|
|
total_len += pending_len
|
|
global_counts += pending_counts
|
|
|
|
if count == 0 or total_len == 0:
|
|
return res
|
|
|
|
res["StringCount"] = float(count)
|
|
res["StringMeanLength"] = float(total_len) / count
|
|
|
|
counts_nonzero = global_counts[global_counts > 0]
|
|
if len(counts_nonzero) > 0:
|
|
res["StringEntropy"] = float(np.log2(total_len) - np.sum(counts_nonzero * np.log2(counts_nonzero)) / total_len)
|
|
|
|
valid_chars = global_counts[0x20:0x7F]
|
|
res.update(dict(zip(cls._STRING_KEYS, valid_chars.astype(np.float64) / total_len)))
|
|
|
|
return res
|
|
|
|
|
|
|
|
@classmethod
|
|
def _extract_histograms(cls, file_bytes):
|
|
arr = np.frombuffer(file_bytes, dtype=np.uint8)
|
|
sz = len(arr)
|
|
res = {}
|
|
|
|
if sz == 0:
|
|
res['FileEntropy'] = 0.0
|
|
res.update(dict.fromkeys(cls._BYTE_HIST_KEYS, 0.0))
|
|
res.update(dict.fromkeys(cls._BYTE_ENT_KEYS, 0.0))
|
|
return res
|
|
|
|
byte_counts = np.zeros(256, dtype=np.int64)
|
|
ent_hist = np.zeros(256, dtype=np.float64)
|
|
window = 2048
|
|
step = 1024
|
|
|
|
if sz < window:
|
|
byte_counts += np.bincount(arr, minlength=256)
|
|
p = byte_counts[byte_counts > 0] / float(sz)
|
|
entropy = float(-np.sum(p * np.log2(p)))
|
|
ent_bin = min(int(entropy * 2.0), 15)
|
|
byte_bins = byte_counts.reshape(16, 16).sum(axis=1)
|
|
idx_start = ent_bin * 16
|
|
ent_hist[idx_start : idx_start+16] += byte_bins
|
|
else:
|
|
num_windows = (sz - window) // step + 1
|
|
|
|
for w_start in range(0, num_windows, cls._HISTOGRAM_BATCH_WINDOWS):
|
|
w_end = min(w_start + cls._HISTOGRAM_BATCH_WINDOWS, num_windows)
|
|
b_num = w_end - w_start
|
|
|
|
start_byte = w_start * step
|
|
end_byte = start_byte + b_num * step + step
|
|
encoded = arr[start_byte:end_byte].astype(np.int32).reshape(b_num + 1, step)
|
|
encoded += np.arange(b_num + 1, dtype=np.int32)[:, None] * 256
|
|
|
|
chunk_counts = np.bincount(encoded.ravel(), minlength=(b_num + 1) * 256).reshape(b_num + 1, 256)
|
|
del encoded
|
|
|
|
byte_counts += np.sum(chunk_counts[:-1], axis=0)
|
|
if w_end == num_windows:
|
|
byte_counts += chunk_counts[-1]
|
|
|
|
window_counts = chunk_counts[:-1] + chunk_counts[1:]
|
|
sum_c_log_c = np.sum(cls._C_LOG_C_TABLE[window_counts], axis=1)
|
|
entropies = 11.0 - sum_c_log_c / 2048.0
|
|
|
|
ent_bins = (entropies * 2.0).astype(np.int32)
|
|
np.clip(ent_bins, 0, 15, out=ent_bins)
|
|
|
|
byte_bins = window_counts.reshape(b_num, 16, 16).sum(axis=2)
|
|
flat_ent_bins = (ent_bins[:, None] * 16 + np.arange(16)).ravel()
|
|
np.add.at(ent_hist, flat_ent_bins, byte_bins.ravel())
|
|
|
|
covered_size = (num_windows + 1) * step
|
|
if covered_size < sz:
|
|
byte_counts += np.bincount(arr[covered_size:], minlength=256)
|
|
|
|
counts_nonzero = byte_counts[byte_counts > 0]
|
|
res['FileEntropy'] = float(np.log2(sz) - np.sum(counts_nonzero * np.log2(counts_nonzero)) / sz)
|
|
|
|
byte_hist = byte_counts.astype(np.float64) / sz
|
|
res.update(dict(zip(cls._BYTE_HIST_KEYS, byte_hist)))
|
|
|
|
ent_sum = np.sum(ent_hist)
|
|
if ent_sum > 0:
|
|
ent_hist /= ent_sum
|
|
|
|
res.update(dict(zip(cls._BYTE_ENT_KEYS, ent_hist)))
|
|
return res
|
|
|
|
|
|
@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, range_entropies=None):
|
|
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 = []
|
|
entropy_iter = iter(range_entropies or ())
|
|
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:
|
|
entropies.append(float(next(entropy_iter)))
|
|
except (StopIteration, TypeError, ValueError):
|
|
entropies.append(0.0)
|
|
|
|
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_security_directory(cls, pe, file_path, fsize):
|
|
res = {"HasSignature": 0.0, "SignatureCount": 0.0}
|
|
if not hasattr(pe, 'OPTIONAL_HEADER') or not hasattr(pe.OPTIONAL_HEADER, 'DATA_DIRECTORY'):
|
|
return res
|
|
directories = pe.OPTIONAL_HEADER.DATA_DIRECTORY
|
|
if len(directories) <= 4:
|
|
return res
|
|
sec_dir = directories[4]
|
|
offset = int(sec_dir.VirtualAddress)
|
|
size = int(sec_dir.Size)
|
|
if offset <= 0 or size <= 0 or offset + size > fsize:
|
|
return res
|
|
|
|
res["HasSignature"] = 1.0
|
|
count = 0
|
|
curr = offset
|
|
end = offset + size
|
|
with open(file_path, "rb") as source:
|
|
while curr + 8 <= end:
|
|
source.seek(curr)
|
|
header = source.read(4)
|
|
if len(header) != 4:
|
|
break
|
|
length = int.from_bytes(header, 'little')
|
|
if length < 8 or curr + length > end:
|
|
break
|
|
count += 1
|
|
curr += (length + 7) & ~7
|
|
res["SignatureCount"] = float(count)
|
|
return res
|
|
|
|
@classmethod
|
|
def extract(cls, file_bytes, file_path, fsize):
|
|
if fsize == 0:
|
|
return None
|
|
|
|
base, dlls, apis, pe = cls._base_defaults(), set(), set(), None
|
|
try:
|
|
pe = pefile.PE(name=file_path, fast_load=True)
|
|
|
|
try:
|
|
pe.parse_rich_header()
|
|
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
|
|
|
|
sections = list(getattr(pe, 'sections', []))
|
|
section_ranges = []
|
|
for section in sections:
|
|
start = max(0, int(section.get_PointerToRawData_adj()))
|
|
end = min(fsize, start + max(0, int(section.SizeOfRawData)))
|
|
section_ranges.append((start, max(start, end)))
|
|
resource_ranges = _collect_resource_ranges(pe, fsize)
|
|
overlay_offset = pe.get_overlay_data_start_offset()
|
|
if not overlay_offset or overlay_offset >= fsize:
|
|
overlay_offset = fsize
|
|
all_ranges = section_ranges + resource_ranges + [
|
|
(int(overlay_offset), fsize)
|
|
]
|
|
stream_features, range_entropies = _extract_stream_features(
|
|
file_path, fsize, all_ranges, cls
|
|
)
|
|
section_entropies = range_entropies[:len(section_ranges)]
|
|
resource_start = len(section_ranges)
|
|
resource_entropies = range_entropies[
|
|
resource_start:resource_start + len(resource_ranges)
|
|
]
|
|
overlay_entropy = range_entropies[-1]
|
|
|
|
base['TrustSigned'] = float(verify_signature(file_path))
|
|
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
|
|
|
|
res_flags_count = dict.fromkeys(cls._CHAR_COUNT_KEYS.values(), 0.0)
|
|
res_flags_ent = dict.fromkeys(cls._CHAR_ENT_KEYS.values(), 0.0)
|
|
res_sec_hash = dict.fromkeys(cls._SECTION_HASH_KEYS, 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_index, section in enumerate(pe.sections):
|
|
sec_name = section.Name.rstrip(b'\x00')
|
|
hash_val = zlib.crc32(sec_name) % 50
|
|
res_sec_hash[cls._SECTION_HASH_KEYS[hash_val]] += 1.0
|
|
|
|
s_entropy = (
|
|
section_entropies[section_index]
|
|
if section_index < len(section_entropies) else 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 cls._CHAR_FLAGS:
|
|
if section.Characteristics & flag:
|
|
res_flags_count[cls._CHAR_COUNT_KEYS[flag]] += 1.0
|
|
res_flags_ent[cls._CHAR_ENT_KEYS[flag]] += 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'] = float(exec_sec)
|
|
base['WritableSections'] = float(write_sec)
|
|
base['ReadableSections'] = float(read_sec)
|
|
base['SectionException'] = float(sec_exc)
|
|
|
|
for flag in cls._CHAR_FLAGS:
|
|
cnt_key = cls._CHAR_COUNT_KEYS[flag]
|
|
if res_flags_count[cnt_key] > 0:
|
|
res_flags_ent[cls._CHAR_ENT_KEYS[flag]] /= res_flags_count[cnt_key]
|
|
|
|
base.update(res_flags_count)
|
|
base.update(res_flags_ent)
|
|
base.update(res_sec_hash)
|
|
|
|
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
|
|
|
|
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'] = float(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'] = float(func_count)
|
|
|
|
base['ExportCount'] = float(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'] = float(icon_count)
|
|
else:
|
|
base['IconCount'] = 0.0
|
|
|
|
base['DebugCount'] = float(len(pe.DIRECTORY_ENTRY_DEBUG)) if hasattr(pe, 'DIRECTORY_ENTRY_DEBUG') else 0.0
|
|
|
|
base.update(stream_features)
|
|
overlay_size = fsize - int(overlay_offset)
|
|
base.update({
|
|
"HasOverlay": 1.0 if overlay_size else 0.0,
|
|
"OverlaySize": float(overlay_size),
|
|
"OverlayRatio": float(overlay_size) / float(fsize) if overlay_size else 0.0,
|
|
"OverlayEntropy": overlay_entropy if overlay_size else 0.0
|
|
})
|
|
base.update(cls._extract_rich_header(pe))
|
|
base.update(cls._extract_ep_anomalies(pe))
|
|
base.update(cls._extract_advanced_resources(pe, resource_entropies))
|
|
base.update(cls._extract_load_config(pe))
|
|
base.update(cls._extract_security_directory(pe, file_path, fsize))
|
|
|
|
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()
|
|
|
|
####################################################################################################
|
|
|
|
def load_existing_hashes():
|
|
hashes = set()
|
|
if not os.path.exists(JSONL_PATH):
|
|
return hashes
|
|
|
|
pattern = re.compile(rb'"FileHash"\s*:\s*"([a-fA-F0-9]{64})"')
|
|
with open(JSONL_PATH, 'rb') as f:
|
|
for line in f:
|
|
match = pattern.search(line)
|
|
if match:
|
|
hashes.add(match.group(1).decode('ascii'))
|
|
|
|
return hashes
|
|
|
|
GLOBAL_HASHES = set()
|
|
|
|
def worker_init(shared_hashes):
|
|
global GLOBAL_HASHES
|
|
GLOBAL_HASHES = shared_hashes
|
|
|
|
def _extract_worker_wrapper(args):
|
|
return _extract_worker(*args)
|
|
|
|
def _extract_worker(file_path, label):
|
|
try:
|
|
fsize = os.path.getsize(file_path)
|
|
if fsize == 0 or fsize > MAX_FILE_SIZE:
|
|
return 'error', None
|
|
|
|
digest = hashlib.sha256()
|
|
with open(file_path, "rb") as source:
|
|
while True:
|
|
chunk = source.read(4194304)
|
|
if not chunk:
|
|
break
|
|
digest.update(chunk)
|
|
sha256 = digest.hexdigest()
|
|
|
|
if sha256 in GLOBAL_HASHES:
|
|
return 'skipped', None
|
|
|
|
res = FeatureExtractor.extract(None, file_path, fsize)
|
|
if res:
|
|
final_res = {"Label": label, "FileHash": sha256, **res}
|
|
return 'success', (sha256, JSON_DUMPS(final_res) + "\n")
|
|
return 'error', None
|
|
except Exception:
|
|
return 'error', None
|
|
|
|
####################################################################################################
|
|
|
|
def scan_and_save(path, label, existing_hashes):
|
|
print(f"\n[*] Scanning path: {path} (Label={label})")
|
|
files = [path] if os.path.isfile(path) else [os.path.join(r, f) for r, _, fs in os.walk(path) for f in fs]
|
|
|
|
total = len(files)
|
|
if total == 0:
|
|
print("[-] No files found.")
|
|
return
|
|
|
|
print(f"[*] Found {total} files. Starting {MAX_WORKERS}-process extraction...\n")
|
|
if HAS_ORJSON:
|
|
print("[+] orjson acceleration enabled.")
|
|
|
|
count, errors, skipped, processed_files = 0, 0, 0, 0
|
|
start_time = time.time()
|
|
batch_buffer = []
|
|
|
|
pool = multiprocessing.Pool(processes=MAX_WORKERS, initializer=worker_init, initargs=(existing_hashes,))
|
|
tasks = [(fpath, label) for fpath in files]
|
|
|
|
try:
|
|
for status, data in pool.imap_unordered(_extract_worker_wrapper, tasks):
|
|
processed_files += 1
|
|
|
|
if status == 'error':
|
|
errors += 1
|
|
elif status == 'skipped':
|
|
skipped += 1
|
|
elif status == 'success':
|
|
sha256, json_str = data
|
|
|
|
if sha256 not in existing_hashes:
|
|
existing_hashes.add(sha256)
|
|
batch_buffer.append(json_str)
|
|
count += 1
|
|
else:
|
|
skipped += 1
|
|
|
|
if len(batch_buffer) >= BATCH_SIZE:
|
|
with open(JSONL_PATH, 'a', encoding='utf-8') as f_out:
|
|
f_out.writelines(batch_buffer)
|
|
batch_buffer.clear()
|
|
|
|
elapsed = time.time() - start_time
|
|
rate = processed_files / elapsed if elapsed > 0 else 0
|
|
sys.stdout.write(f"\r[{processed_files}/{total}] Added: {count} | Skipped: {skipped} | Errors: {errors} | Speed: {rate:.1f} files/s")
|
|
sys.stdout.flush()
|
|
|
|
pool.close()
|
|
pool.join()
|
|
|
|
except KeyboardInterrupt:
|
|
print("\n\n[-] User aborted. Force terminating all child processes...")
|
|
pool.terminate()
|
|
pool.join()
|
|
|
|
except Exception as e:
|
|
print(f"\n[-] Critical error: {e}")
|
|
pool.terminate()
|
|
pool.join()
|
|
|
|
finally:
|
|
if batch_buffer:
|
|
try:
|
|
with open(JSONL_PATH, 'a', encoding='utf-8') as f_out:
|
|
f_out.writelines(batch_buffer)
|
|
except Exception as save_err:
|
|
print(f"\n[-] Failed to save remaining buffer: {save_err}")
|
|
|
|
print(f"\n\n[+] Scan complete. Total added: {count}, Total skipped: {skipped}")
|
|
|
|
####################################################################################################
|
|
|
|
if __name__ == "__main__":
|
|
multiprocessing.freeze_support()
|
|
|
|
print("\n---------------- PE Dataset Builder v4.0 ----------------\n")
|
|
|
|
existing_hashes = load_existing_hashes()
|
|
print(f"[+] Found {len(existing_hashes)} existing hashes.\n")
|
|
|
|
try:
|
|
while True:
|
|
print("-" * 57)
|
|
target_path = input("\n[*] Enter path (file or directory): ").strip().strip('"').strip("'")
|
|
if target_path.lower() in ['exit', 'q']:
|
|
break
|
|
|
|
if not target_path or not os.path.exists(target_path):
|
|
print("[-] Invalid path.")
|
|
continue
|
|
|
|
while True:
|
|
label_input = input("[*] Enter label (0=Safe, 1=Malware): ").strip()
|
|
if label_input.lower() in ['exit', 'q']:
|
|
sys.exit()
|
|
if label_input in ['0', '1']:
|
|
break
|
|
|
|
print("[-] Please enter 0 or 1.")
|
|
|
|
scan_and_save(target_path, int(label_input), existing_hashes)
|
|
|
|
except KeyboardInterrupt:
|
|
print("\n\n[-] Aborted.")
|