forked from hellman/xortool
/
xortool.py
executable file
·292 lines (237 loc) · 8.53 KB
/
xortool.py
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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
#!/usr/bin/env python
#-*- coding:utf-8 -*-
# ---------------------------------------------------------------
# xortool.py
# A tool to do some xor analysis:
# - guess the key length (based on count of equal chars)
# - guess the key (base on knowledge of most frequent char)
# Usage:
# xortool [-h|--help] [OPTIONS] [<filename>]
# Options:
# -l,--key-length length of the key (integer)
# -c,--char most frequent char (one char or hex code)
# -m,--max-keylen=65 maximum key length to probe (integer)
# -x,--hex input is hex-encoded str
# Examples:
# xortool file.bin
# xortool -x -l 4 -c ' ' file.hex
# ---------------------------------------------------------------
# Author: hellman ( hellman1908@gmail.com )
# License: GNU GPL v2 ( http://opensource.org/licenses/gpl-2.0.php )
# ---------------------------------------------------------------
import os
import sys
import math
from colors import *
from routine import *
from args import parse_parameters, ArgError
DIRNAME = 'xortool_out' # here plaintexts will be placed
PARAMETERS = dict()
def main():
global PARAMETERS
try:
PARAMETERS = parse_parameters()
ciphertext = get_ciphertext()
update_key_length(ciphertext)
probable_keys = guess_probable_keys(ciphertext)
print_keys(probable_keys)
produce_plaintexts(ciphertext, probable_keys)
except IOError as err:
print C_FATAL + "[ERROR] Can't load file:\n\t", err, C_RESET
except ArgError as err:
print C_FATAL + "[ERROR] Bad argument:\n\t", err, C_RESET
except MkdirError as err:
print C_FATAL + "[ERROR] Can't create directory:\n\t", err, C_RESET
else:
return
cleanup()
# -----------------------------------------------------------------------------
# LOADING CIPHERTEXT
# -----------------------------------------------------------------------------
def get_ciphertext():
"""
Load ciphertext from a file or stdin and hex-decode if needed
"""
ciphertext = load_file(PARAMETERS["filename"])
if PARAMETERS["input_is_hex"]:
ciphertext = decode_from_hex(ciphertext)
return ciphertext
# -----------------------------------------------------------------------------
# KEYLENGTH GUESSING SECTION
# -----------------------------------------------------------------------------
def update_key_length(text):
"""
Guess length of the key if it's not set. (Updates PARAMETERS)
"""
global PARAMETERS
if PARAMETERS["known_key_length"]:
return
PARAMETERS["known_key_length"] = guess_key_length(text)
return
def guess_key_length(text):
"""
Try key lengths from 1 to max_key_length and print local maximums.
Set key_length to the most possible if it's not set by user.
"""
fitnesses = calculate_fitnesses(text)
print_fitnesses(fitnesses)
guess_and_print_divizors(fitnesses)
return get_max_fitnessed_key_length(fitnesses)
def calculate_fitnesses(text):
"""
Calc. fitnesses for each keylen
"""
prev = 0
pprev = 0
fitnesses = []
for key_length in range(1, PARAMETERS["max_key_length"] + 1):
fitness = count_equals(text, key_length)
fitness = float(fitness) / (64 + key_length ** 0.5)
if pprev < prev and prev > fitness: # local maximum
fitnesses += [(key_length - 1, prev)]
pprev = prev
prev = fitness
return fitnesses
def print_fitnesses(fitnesses):
print "The most probable key lengths:"
#fitness_sum = calculate_fitness_sum(fitnesses)
# top sorted by fitness, but print sorted by length
fitnesses.sort(key=lambda a: a[1], reverse=True)
top10 = fitnesses[:10]
best_fitness = top10[0][1]
top10.sort(key=lambda a: a[0])
fitness_sum = calculate_fitness_sum(top10)
for key_length, fitness in top10:
s1 = str(key_length).rjust(4, " ")
s2 = str(round(100 * fitness * 1.0 / fitness_sum, 1)) + "%"
if fitness == best_fitness:
print C_BEST_KEYLEN + s1 + C_RESET + ": ",
print C_BEST_PROB + s2 + C_RESET
else:
print C_KEYLEN + s1 + C_RESET + ": ",
print C_PROB + s2 + C_RESET
return
def calculate_fitness_sum(fitnesses):
return sum([f for (key_length, f) in fitnesses])
def count_equals(text, key_length):
"""
count equal chars count for each offset and sum them
"""
equals_count = 0
if key_length >= len(text):
return 0
for offset in range(key_length):
chars_count = chars_count_at_offset(text, key_length, offset)
equals_count += max(chars_count.values()) - 1 # why -1? don't know
return equals_count
def guess_and_print_divizors(fitnesses):
"""
Prints common divizors and returns the most common divizor
"""
divizors_counts = [0 for i in range(PARAMETERS["max_key_length"] + 1)]
for key_length, fitness in fitnesses:
for number in range(3, key_length + 1):
if key_length % number == 0:
divizors_counts[number] += 1
max_divizors = max(divizors_counts)
limit = 3
ret = 2
for number, divizors_count in enumerate(divizors_counts):
if divizors_count == max_divizors:
print "Key-length can be " + C_DIV + str(number) + "*n" + C_RESET
ret = number
limit -= 1
if limit == 0:
return ret
return ret
def get_max_fitnessed_key_length(fitnesses):
max_fitness = 0
max_fitnessed_key_length = 0
for key_length, fitness in fitnesses:
if fitness > max_fitness:
max_fitness = fitness
max_fitnessed_key_length = key_length
return max_fitnessed_key_length
def chars_count_at_offset(text, key_length, offset):
chars_count = dict()
for pos in range(offset, len(text), key_length):
c = text[pos]
if c in chars_count:
chars_count[c] += 1
else:
chars_count[c] = 1
return chars_count
# -----------------------------------------------------------------------------
# KEYS GUESSING SECTION
# -----------------------------------------------------------------------------
def guess_probable_keys(text):
"""
Guess key if the most frequent char is known.
"""
probable_keys = []
if PARAMETERS["most_frequent_char"] is None:
die(C_WARN + "Most possible char is needed to guess the key!" + C_RESET)
else:
probable_keys = guess_keys(text)
return probable_keys
def guess_keys(text):
"""
Generate all possible keys for key length
and the most possible char
"""
key_length = PARAMETERS["known_key_length"]
most_char = PARAMETERS["most_frequent_char"]
key_possible_bytes = [[] for i in range(key_length)]
for offset in range(key_length): # each byte of key<
chars_count = chars_count_at_offset(text, key_length, offset)
max_count = max(chars_count.values())
for char in chars_count:
if chars_count[char] >= max_count:
key_possible_bytes[offset] += chr(ord(char) ^ most_char)
return all_keys(key_possible_bytes)
def all_keys(key_possible_bytes, key_part="", offset=0):
"""
Produce all combinations of possible key chars
"""
keys = []
if offset >= len(key_possible_bytes):
return [key_part]
for c in key_possible_bytes[offset]:
keys += all_keys(key_possible_bytes, key_part + c, offset + 1)
return keys
def print_keys(keys):
if not keys:
print "No keys guessed!"
return
s1 = C_COUNT + str(len(keys)) + C_RESET
s2 = C_COUNT + str(len(keys[0])) + C_RESET
print "{0} possible key(s) of length {1}:".format(s1, s2)
for key in keys[:5]:
print C_KEY + repr(key)[1:-1] + C_RESET
if len(keys) > 10:
print "..."
# -----------------------------------------------------------------------------
# PRODUCE OUTPUT
# -----------------------------------------------------------------------------
def produce_plaintexts(ciphertext, keys):
"""
Produce plaintext variant for each possible key
"""
cleanup()
mkdir(DIRNAME)
for index, key in enumerate(keys):
key_index = str(index).rjust(len(str(len(keys) - 1)), "0")
key_repr = repr(key)[1:-1].replace("/", "\\x2f")
if not is_linux():
key_repr = alphanum(key)
file_name = os.path.join(DIRNAME, key_index + "_" + key_repr)
f = open(file_name, "wb")
f.write(dexor(ciphertext, key))
f.close()
return
def cleanup():
if os.path.exists(DIRNAME):
rmdir(DIRNAME)
return
if __name__ == "__main__":
main()