py2.7可行版本
This commit is contained in:
parent
8063d079db
commit
65d25d42de
@ -1,4 +1,5 @@
|
|||||||
# coding=utf-8
|
# coding=utf-8
|
||||||
|
import hashlib
|
||||||
import pickle as pk
|
import pickle as pk
|
||||||
import re
|
import re
|
||||||
import json
|
import json
|
||||||
@ -6,125 +7,133 @@ import os
|
|||||||
from tqdm import tqdm
|
from tqdm import tqdm
|
||||||
|
|
||||||
|
|
||||||
def convert(start, end, overhaul):
|
def calc_sha256(file_path):
|
||||||
for workflow in range(start, end):
|
with open(file_path, 'rb') as f:
|
||||||
# workflow = 0
|
bytes = f.read()
|
||||||
cfg_dir = "D:\\hkn\\infected\\datasets\\virusshare_infected{}_cfg".format(workflow)
|
sha256obj = hashlib.sha256(bytes)
|
||||||
output_dir = "D:\\hkn\\infected\\datasets\\virusshare_infected{}_json".format(workflow)
|
sha256 = sha256obj.hexdigest()
|
||||||
dot_dir = "D:\\hkn\\infected\\datasets\\virusshare_infected{}_dot".format(workflow)
|
return sha256
|
||||||
|
|
||||||
log_path = "D:\\hkn\\infected\\datasets\\logging\\convert_log{}.log".format(workflow)
|
|
||||||
process_log_path = "D:\\hkn\\infected\\datasets\\logging\\convert_process_log{}.log".format(workflow)
|
|
||||||
|
|
||||||
if overhaul:
|
def convert_malware(overhaul):
|
||||||
if os.path.exists(log_path):
|
cfg_dir = "D:\\bishe\\dataset\\infected\\infected_cfg"
|
||||||
os.remove(log_path)
|
output_dir = "D:\\bishe\\dataset\\infected\\infected_jsonl"
|
||||||
if os.path.exists(process_log_path):
|
dot_dir = "D:\\bishe\\dataset\\infected\\infected_dot"
|
||||||
os.remove(process_log_path)
|
raw_dir = "D:\\bishe\\dataset\\train_malware"
|
||||||
|
|
||||||
with open(log_path, 'a+') as log, open(process_log_path, 'a+') as process_log:
|
log_path = "D:\\bishe\\dataset\\logging\\convert_malware_log.log"
|
||||||
logged = log.readline()
|
process_log_path = "D:\\bishe\\dataset\\logging\\convert_malware_process_log.log"
|
||||||
if logged == '':
|
|
||||||
log_index = 0
|
if overhaul:
|
||||||
|
if os.path.exists(log_path):
|
||||||
|
os.remove(log_path)
|
||||||
|
if os.path.exists(process_log_path):
|
||||||
|
os.remove(process_log_path)
|
||||||
|
|
||||||
|
with open(log_path, 'a+') as log, open(process_log_path, 'a+') as process_log:
|
||||||
|
logged = log.readline()
|
||||||
|
if logged == '':
|
||||||
|
log_index = 0
|
||||||
|
else:
|
||||||
|
log_index = int(logged)
|
||||||
|
|
||||||
|
for index, cfg in enumerate(tqdm(os.listdir(cfg_dir))):
|
||||||
|
if index < log_index:
|
||||||
|
continue
|
||||||
|
|
||||||
|
name = cfg[:-4] # 纯文件名，不带后缀
|
||||||
|
cfg_file = open(os.path.join(cfg_dir, name + '.ida'), 'r')
|
||||||
|
try:
|
||||||
|
data = pk.load(cfg_file)
|
||||||
|
except EOFError:
|
||||||
|
process_log.write("index {}, {} process failed. EOFError occurred.\n".format(index, cfg))
|
||||||
|
continue
|
||||||
|
except ValueError:
|
||||||
|
process_log.write("index {}, {} process failed. ValueError occurred.\n".format(index, cfg))
|
||||||
|
continue
|
||||||
|
finally:
|
||||||
|
cfg_file.close()
|
||||||
|
|
||||||
|
dot_file_path = os.path.join(dot_dir, name + '.dot')
|
||||||
|
if not os.path.exists(dot_file_path):
|
||||||
|
process_log.write("index {}, {} process failed. dot file not exists.\n".format(index, cfg))
|
||||||
else:
|
else:
|
||||||
log_index = int(logged)
|
# 打开dot文件获取fcg
|
||||||
|
raw_function_edges = []
|
||||||
|
# 2023.8.12 bug fix: ida生成的fcg(.dot)文件包含了所有函数，data.raw_graph_list仅包含了内部函数
|
||||||
|
functions_list = []
|
||||||
|
with open(dot_file_path, 'r') as dot:
|
||||||
|
for line in dot:
|
||||||
|
if '->' in line:
|
||||||
|
raw_function_edges.append(re.findall(r'\b\d+\b', line))
|
||||||
|
elif 'label' in line:
|
||||||
|
functions_list.append(line[line.find('= "') + 3:line.find('",')])
|
||||||
|
|
||||||
for index, cfg in enumerate(tqdm(os.listdir(cfg_dir))):
|
# 没有内部函数被检测到，正常来说不应该，保险起见还是不要这数据了
|
||||||
if index < log_index:
|
if raw_function_edges.__len__() == 0:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
name = cfg[:-4] # 纯文件名，不带后缀
|
# 为当前pe文件创建json对象
|
||||||
cfg_file = open(os.path.join(cfg_dir, name + '.ida'), 'r')
|
json_obj = {
|
||||||
try:
|
'hash': calc_sha256(raw_dir + "\\" + name),
|
||||||
data = pk.load(cfg_file)
|
# 2023.8.12 bug fix: 这里获取的是内部函数的数量
|
||||||
except EOFError:
|
# 'function_number': data.raw_graph_list.__len__(),
|
||||||
process_log.write("index {}, {} process failed. EOFError occurred.\n".format(index, cfg))
|
'function_number': len(functions_list),
|
||||||
continue
|
'function_edges': [[int(d[0]) for d in raw_function_edges],
|
||||||
except ValueError:
|
[int(d[1]) for d in raw_function_edges]],
|
||||||
process_log.write("index {}, {} process failed. ValueError occurred.\n".format(index, cfg))
|
'acfg_list': [],
|
||||||
continue
|
'function_names': functions_list
|
||||||
finally:
|
}
|
||||||
cfg_file.close()
|
|
||||||
|
|
||||||
dot_file_path = os.path.join(dot_dir, name + '.dot')
|
# 2023.8.12 bug fix: data.raw_graph_list是ida检测到的内部函数，不包括外部函数，因此函数列表和函数数量不能从这里获取
|
||||||
if not os.path.exists(dot_file_path):
|
# 读取pkl文件，一个acfg由一个函数分解而来
|
||||||
process_log.write("index {}, {} process failed. dot file not exists.\n".format(index, cfg))
|
for acfg in data.raw_graph_list:
|
||||||
else:
|
# 函数为外部函数，不需要构建cfg
|
||||||
# 打开dot文件获取fcg
|
if acfg.funcname != 'start' and acfg.funcname != 'start_0' and 'sub_' not in acfg.funcname:
|
||||||
raw_function_edges = []
|
|
||||||
# 2023.8.12 bug fix: ida生成的fcg(.dot)文件包含了所有函数，data.raw_graph_list仅包含了内部函数
|
|
||||||
functions_list = []
|
|
||||||
with open(dot_file_path, 'r') as dot:
|
|
||||||
for line in dot:
|
|
||||||
if '->' in line:
|
|
||||||
raw_function_edges.append(re.findall(r'\b\d+\b', line))
|
|
||||||
elif 'label' in line:
|
|
||||||
functions_list.append(line[line.find('= "') + 3:line.find('",')])
|
|
||||||
|
|
||||||
# 没有内部函数被检测到，正常来说不应该，保险起见还是不要这数据了
|
|
||||||
if raw_function_edges.__len__() == 0:
|
|
||||||
continue
|
continue
|
||||||
|
|
||||||
# 为当前pe文件创建json对象
|
# 这里2是因为Genius框架提取特征时将后代数量放在2
|
||||||
json_obj = {
|
offspring = [d.get('v')[2] for d in acfg.g.node.values()]
|
||||||
'hash': data.binary_name[11:],
|
# 这边可能会出现不知名的原因两个数组长度不一致，按理来说应该是一致的
|
||||||
# 2023.8.12 bug fix: 这里获取的是内部函数的数量
|
# 以框架为主，将bb_features数组削减为和g.node长度一致
|
||||||
# 'function_number': data.raw_graph_list.__len__(),
|
diff = acfg.g.__len__() - len(acfg.bb_features)
|
||||||
'function_number': len(functions_list),
|
if diff != 0:
|
||||||
'function_edges': [[int(d[0]) for d in raw_function_edges],
|
del acfg.bb_features[diff:]
|
||||||
[int(d[1]) for d in raw_function_edges]],
|
# 将后代数量的特征放入bb_features中
|
||||||
'acfg_list': [],
|
|
||||||
'function_names': functions_list
|
for i, offs in enumerate(offspring):
|
||||||
|
acfg.bb_features[i].append(offs)
|
||||||
|
|
||||||
|
acfg_item = {
|
||||||
|
'block_number': acfg.g.__len__(),
|
||||||
|
'block_edges': [[d[0] for d in acfg.g.edges], [d[1] for d in acfg.g.edges]],
|
||||||
|
'block_features': acfg.bb_features
|
||||||
}
|
}
|
||||||
|
|
||||||
# 2023.8.12 bug fix: data.raw_graph_list是ida检测到的内部函数，不包括外部函数，因此函数列表和函数数量不能从这里获取
|
json_obj['acfg_list'].append(acfg_item)
|
||||||
# 读取pkl文件，一个acfg由一个函数分解而来
|
# json_obj['function_names'].append(acfg.funcname)
|
||||||
for acfg in data.raw_graph_list:
|
|
||||||
# 函数为外部函数，不需要构建cfg
|
|
||||||
if acfg.funcname != 'start' and acfg.funcname != 'start_0' and 'sub_' not in acfg.funcname:
|
|
||||||
continue
|
|
||||||
|
|
||||||
# 这里2是因为Genius框架提取特征时将后代数量放在2
|
# 将结果写入json本地文件
|
||||||
offspring = [d.get('v')[2] for d in acfg.g.node.values()]
|
result = json.dumps(json_obj, ensure_ascii=False)
|
||||||
# 这边可能会出现不知名的原因两个数组长度不一致，按理来说应该是一致的
|
|
||||||
# 以框架为主，将bb_features数组削减为和g.node长度一致
|
|
||||||
diff = acfg.g.__len__() - len(acfg.bb_features)
|
|
||||||
if diff != 0:
|
|
||||||
del acfg.bb_features[diff:]
|
|
||||||
# 将后代数量的特征放入bb_features中
|
|
||||||
|
|
||||||
for i, offs in enumerate(offspring):
|
with open(os.path.join(output_dir, name + '.jsonl'), 'w') as out:
|
||||||
acfg.bb_features[i].append(offs)
|
out.write(result)
|
||||||
|
|
||||||
acfg_item = {
|
log.truncate(0)
|
||||||
'block_number': acfg.g.__len__(),
|
log.seek(0)
|
||||||
'block_edges': [[d[0] for d in acfg.g.edges], [d[1] for d in acfg.g.edges]],
|
log.write(str(index))
|
||||||
'block_features': acfg.bb_features
|
log.flush()
|
||||||
}
|
process_log.write("index {}, {} process done.\n".format(index, cfg))
|
||||||
|
|
||||||
json_obj['acfg_list'].append(acfg_item)
|
|
||||||
# json_obj['function_names'].append(acfg.funcname)
|
|
||||||
|
|
||||||
# 将结果写入json本地文件
|
|
||||||
result = json.dumps(json_obj, ensure_ascii=False)
|
|
||||||
|
|
||||||
with open(os.path.join(output_dir, name + '.jsonl'), 'w') as out:
|
|
||||||
out.write(result)
|
|
||||||
|
|
||||||
log.truncate(0)
|
|
||||||
log.seek(0)
|
|
||||||
log.write(str(index))
|
|
||||||
log.flush()
|
|
||||||
process_log.write("index {}, {} process done.\n".format(index, cfg))
|
|
||||||
|
|
||||||
|
|
||||||
def convert_benign(overhaul):
|
def convert_benign(overhaul):
|
||||||
cfg_dir = "F:\\kkk\\dataset\\benign\\refind_cfg"
|
cfg_dir = "D:\\bishe\\dataset\\benign\\refind_cfg"
|
||||||
dot_dir = "F:\\kkk\\dataset\\benign\\refind_dot"
|
dot_dir = "D:\\bishe\\dataset\\benign\\refind_dot"
|
||||||
output_dir = "F:\\kkk\\dataset\\benign\\refind_jsonl"
|
output_dir = "D:\\bishe\\dataset\\benign\\refind_jsonl"
|
||||||
|
raw_dir = "D:\\bishe\\dataset\\train_benign"
|
||||||
|
|
||||||
log_path = "D:\\hkn\\infected\\datasets\\logging\\convert_benign_log.log"
|
log_path = "D:\\bishe\\dataset\\logging\\convert_benign_log.log"
|
||||||
process_log_path = "D:\\hkn\\infected\\datasets\\logging\\convert_benign_process_log{}.log"
|
process_log_path = "D:\\bishe\\dataset\\logging\\convert_benign_process_log.log"
|
||||||
|
|
||||||
if overhaul:
|
if overhaul:
|
||||||
if os.path.exists(log_path):
|
if os.path.exists(log_path):
|
||||||
@ -145,6 +154,7 @@ def convert_benign(overhaul):
|
|||||||
continue
|
continue
|
||||||
|
|
||||||
name = cfg[:-4] # 纯文件名
|
name = cfg[:-4] # 纯文件名
|
||||||
|
|
||||||
cfg_file = open(os.path.join(cfg_dir, name + '.ida'), 'r')
|
cfg_file = open(os.path.join(cfg_dir, name + '.ida'), 'r')
|
||||||
try:
|
try:
|
||||||
data = pk.load(cfg_file)
|
data = pk.load(cfg_file)
|
||||||
@ -180,7 +190,7 @@ def convert_benign(overhaul):
|
|||||||
|
|
||||||
# 为当前pe文件创建json对象
|
# 为当前pe文件创建json对象
|
||||||
json_obj = {
|
json_obj = {
|
||||||
'hash': data.binary_name[11:],
|
'hash': calc_sha256(raw_dir + "\\" + name),
|
||||||
# 2023.8.12 bug fix: 这里获取的是内部函数的数量
|
# 2023.8.12 bug fix: 这里获取的是内部函数的数量
|
||||||
# 'function_number': data.raw_graph_list.__len__(),
|
# 'function_number': data.raw_graph_list.__len__(),
|
||||||
'function_number': len(functions_list),
|
'function_number': len(functions_list),
|
||||||
@ -233,4 +243,6 @@ def convert_benign(overhaul):
|
|||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
# convert(35, 69)
|
# convert(35, 69)
|
||||||
convert_benign(False)
|
# convert_benign(True)
|
||||||
|
convert_benign(True)
|
||||||
|
convert_malware(True)
|
||||||
Loading…
Reference in New Issue
Block a user