data_obfuscator.py
3.87 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
from utils import *
import file_parser
import re
# obfuscator v1 uses names from other methods (shuffles method names)
def detect_vars(line): # detect variables and return range tuples. except for keywords
ret = list()
s = 0
e = 0
detected = False
strException = False
strCh = None
line += ' ' # for last separator
for i in range(len(line)):
c = line[i]
if not strException and (c == "'" or c == '"'): # we cannot remove string first, because index gets changed
strCh = c
strException = True
continue
if strException:
if c == strCh:
strException = False
continue
if not detected and re.match('[A-Za-z_]', c):
detected = True
s = i
continue
if detected and not re.match('[A-Za-z_0-9]', c):
detected = False
e = i
ret.append((s, e))
return ret
def obfuscate(lines, vars, dictionary, mapper): # obfuscate the code
ret = list()
for line in lines:
var_ranges = detect_vars(line)
var_ranges = [(s, e) for (s, e) in var_ranges if line[s:e] in vars] # remove keywords (do not convert to words because of string exception)
var_ranges.append((-1, -1)) # for out-of-range exception
var_index = 0
new_line = ''
i = 0
L = len(line)
while i < L:
if i == var_ranges[var_index][0]: # found var
s, e = var_ranges[var_index]
new_line += vars[mapper[dictionary[line[s:e]]]]
i = e
var_index += 1
else:
new_line += line[i]
i += 1
ret.append(new_line)
return ret
def create_var_histogram(input, outPath):
files = [f for f in readdir(input) if is_extension(f, 'py')]
freq_dict = dict()
for p in files:
lines = read_file(p)
lines = remove_unnecessary_comments(lines)
for line in lines:
file_parser.parse_keywords(line, freq_dict)
hist = open(outPath, 'w', encoding='utf8')
arr = sorted(freq_dict.items(), key=select_value)
for i in arr:
hist.write(str(i) + '\n')
hist.close()
def read_histogram(inputPath):
lines = read_file(inputPath)
ret = []
for line in lines:
line = line.split("'")[1]
ret.append(line)
return ret
def obfuscate_files(input, output, var=None, threshold=4000): # obfuscate variables. Guessing variable names from keyword frequency (threshold) if variable list is not given
files = [f for f in readdir(input) if is_extension(f, 'py')]
freq_dict = dict()
codes = list()
for p in files:
lines = read_file(p)
lines = remove_unnecessary_comments(lines) # IMPORTANT: remove comments from lines for preprocessing
codes.append((p, lines))
if var == None:
for line in lines:
file_parser.parse_keywords(line, freq_dict)
if var == None: # don't have variable list
hist = open(os.path.join(output, 'log.txt'), 'w', encoding='utf8')
arr = sorted(freq_dict.items(), key=select_value)
for i in arr:
hist.write(str(i) + '\n')
hist.close()
var, _ = threshold_dict(freq_dict, threshold)
var = [v[0] for v in var]
dictionary = create_dictionary(var)
mapper = create_mapper(len(var))
for path, code in codes:
obfuscated = obfuscate(code, var, dictionary, mapper)
filepath = path.split(input)[1][1:]
os.makedirs(os.path.join(output, filepath.split('\\')[0]), exist_ok=True) # create the output directory if not exists
new_path = os.path.join(output, filepath)
write_file(new_path, obfuscated)
print("Done generating Obfuscated Dataset")
'''
Usage
obfuscate_files('data/original', 'data/obfuscated')
'''