├── qlpack.yml
├── test-data
├── data.csv.gz
├── php_php-fuzz-parser_ranking.svg
├── libpcap_fuzz_both_ranking.svg
├── freetype2-2017_ranking.svg
└── libxml2-v2.9.2_ranking.svg
├── array-literals.ql
├── local-variables.ql
├── Global-values.ql
├── globals-values.ql
├── memcmpvals.ql
├── strstrvals.ql
├── strcmpvals.ql
├── magic-values.ql
├── strtool.ql
├── regex-values.ql
├── README.md
├── MIT-License.txt
├── Global-values.py
├── magic-values.py
├── memcmpvals.py
├── regex-values.py
├── strcmpvals.py
├── strstrvals.py
├── array-literals.py
├── local-variables.py
└── run.py
/qlpack.yml:
--------------------------------------------------------------------------------
1 | name: fuzzingdriver
2 | version: 0.0.0
3 | libraryPathDependencies: codeql-cpp
4 |
--------------------------------------------------------------------------------
/test-data/data.csv.gz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/cryptomadco/fuzzingdriver/HEAD/test-data/data.csv.gz
--------------------------------------------------------------------------------
/array-literals.ql:
--------------------------------------------------------------------------------
1 | import cpp
2 |
3 | from ArrayAggregateLiteral a
4 |
5 | select a.getElementExpr(_).getValueText()
6 |
--------------------------------------------------------------------------------
/local-variables.ql:
--------------------------------------------------------------------------------
1 | import cpp
2 |
3 | from LocalVariable v
4 |
5 | select v.getAnAssignedValue().getValueText()
6 |
--------------------------------------------------------------------------------
/Global-values.ql:
--------------------------------------------------------------------------------
1 |
2 | import cpp
3 |
4 | from GlobalVariable gb
5 |
6 | select gb.getAnAssignedValue().getValueText().toString()
7 |
--------------------------------------------------------------------------------
/globals-values.ql:
--------------------------------------------------------------------------------
1 | /**
2 | * @kind problem
3 | */
4 | import cpp
5 |
6 | from GlobalVariable gb
7 |
8 | select gb.getAnAssignedValue().getValueText().toString()
9 |
--------------------------------------------------------------------------------
/memcmpvals.ql:
--------------------------------------------------------------------------------
1 | import cpp
2 | from FunctionCall fucall, Expr size
3 | where
4 | fucall.getTarget().hasName("memcmp")
5 | select fucall.getArgument(_).getValueText()
6 |
--------------------------------------------------------------------------------
/strstrvals.ql:
--------------------------------------------------------------------------------
1 | import cpp
2 | from FunctionCall fucall, Expr size
3 | where
4 | fucall.getTarget().hasName("strstr")
5 | select fucall.getArgument(_).getValueText()
6 |
--------------------------------------------------------------------------------
/strcmpvals.ql:
--------------------------------------------------------------------------------
1 |
2 | import cpp
3 | from FunctionCall fucall, Expr size
4 | where
5 | fucall.getTarget().hasName("strncmp")
6 | select fucall.getArgument(_).getValueText()
7 |
--------------------------------------------------------------------------------
/magic-values.ql:
--------------------------------------------------------------------------------
1 | import cpp
2 |
3 | class HexOrOctLiteral extends Literal{
4 | HexOrOctLiteral(){
5 | (this instanceof HexLiteral) or (this instanceof OctalLiteral)
6 | }
7 | }
8 |
9 | from HexOrOctLiteral lit
10 | select lit.getValueText()
11 |
--------------------------------------------------------------------------------
/strtool.ql:
--------------------------------------------------------------------------------
1 | import cpp
2 | import semmle.code.cpp.dataflow.DataFlow
3 | class StringLiteralNode extends DataFlow::Node {
4 | StringLiteralNode() { this.asExpr() instanceof StringLiteral }
5 | }
6 | class MemcmpArgNode extends DataFlow::Node {
7 | MemcmpArgNode() {
8 | exists(FunctionCall fc |
9 | fc.getTarget().getName().regexpMatch(".*(str|mem|strn|b)*(cmp|str)*") and
10 | fc.getArgument(0) = this.asExpr()
11 | )
12 | or
13 | exists(FunctionCall fc |
14 | fc.getTarget().getName().regexpMatch(".*(str|mem|strn|b)*(cmp|str)*") and
15 | fc.getArgument(1) = this.asExpr()
16 | )
17 | }
18 | }
19 |
20 | from StringLiteralNode src, MemcmpArgNode arg
21 | where
22 | DataFlow::localFlow(src, arg)
23 |
24 | select src.asExpr().(StringLiteral).toString()
25 |
--------------------------------------------------------------------------------
/regex-values.ql:
--------------------------------------------------------------------------------
1 | import cpp
2 | import semmle.code.cpp.dataflow.DataFlow
3 | class StringLiteralNode extends DataFlow::Node {
4 | StringLiteralNode() { this.asExpr() instanceof StringLiteral }
5 | }
6 | class MemcmpArgNode extends DataFlow::Node {
7 | MemcmpArgNode() {
8 | exists(FunctionCall fc |
9 | fc.getTarget().getName().regexpMatch(".*(str|mem|strn|b)*(cmp|str)*") and
10 | fc.getArgument(0) = this.asExpr()
11 | )
12 | or
13 | exists(FunctionCall fc |
14 | fc.getTarget().getName().regexpMatch(".*(str|mem|strn|b)*(cmp|str)*") and
15 | fc.getArgument(1) = this.asExpr()
16 | )
17 | }
18 | }
19 |
20 | from StringLiteralNode src, MemcmpArgNode arg
21 | where
22 | DataFlow::localFlow(src, arg)
23 |
24 | select src.asExpr().(StringLiteral).toString()
25 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # FuzzingDriver
2 |
3 | [FuzzingDriver: the Missing Dictionary to Increase Code Coverage in Fuzzers, SANER'22](https://arxiv.org/pdf/2201.04853.pdf)
4 |
5 |
6 | We propose a tool, called FuzzingDriver, to generate dictionary tokens for coverage-based greybox fuzzers (CGF) from the codebase of any target program. FuzzingDriver does not add any overhead to the fuzzing job as it is run beforehand. We compared FuzzingDriver to Google dictionaries by fuzzing six open-source targets, and we found that FuzzingDriver consistently achieves higher code coverage in all tests. We also executed eight benchmarks on FuzzBench to demonstrate how utilizing FuzzingDriver's dictionaries can outperform six widely-used CGF fuzzers. In future work, investigating the impact of FuzzingDriver's dictionaries on improving bug coverage might prove important.
7 |
8 | [Video demonstration](https://www.youtube.com/watch?v=Y8j_KvfRrI8)
9 |
--------------------------------------------------------------------------------
/MIT-License.txt:
--------------------------------------------------------------------------------
1 | MIT License
2 |
3 | Copyright (c) [2022] [FuzzingDriver]
4 |
5 | Permission is hereby granted, free of charge, to any person obtaining a copy
6 | of this software and associated documentation files (the "Software"), to deal
7 | in the Software without restriction, including without limitation the rights
8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 |
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 |
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 |
--------------------------------------------------------------------------------
/Global-values.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-globals{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/magic-values.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-magic{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/memcmpvals.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-memcmp{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/regex-values.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-regex{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/strcmpvals.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-strcmp{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/strstrvals.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-strstr{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/array-literals.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-arrlits{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/local-variables.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 |
3 | #####################################################################
4 | # FuzzingDriver #
5 | # The missing dictionary to increase code coverage in fuzzers #
6 | #####################################################################
7 |
8 | import os
9 | import string
10 | import binascii
11 | import codecs
12 | import errno
13 | import struct
14 | import argparse
15 | import re
16 | from binascii import unhexlify
17 |
18 |
19 | def ensure_dir(dir):
20 | try:
21 | os.makedirs(dir)
22 | except OSError as e:
23 | if e.errno != errno.EEXIST:
24 | raise
25 |
26 |
27 | def parse_args():
28 | parser = argparse.ArgumentParser(
29 | description=(
30 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python2 thisfile.py outdir str.txt"
31 | )
32 | )
33 | parser.add_argument(
34 | "corpdir", help="The path to the corpus directory to generate strings."
35 | )
36 | parser.add_argument(
37 | "infile",
38 | help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt",
39 | )
40 |
41 | return parser.parse_args()
42 |
43 |
44 | def do_string_analysis(corpdir, infile1):
45 | with open(infile1, "r") as f1:
46 | lines = f1.readlines()[1:]
47 | f1.close()
48 | new_lst1 = []
49 | n = 1
50 | for i, num1 in enumerate(lines):
51 | if i != 0:
52 | new_lst1.append(num1)
53 | # print("num : %s" % num1)
54 | str11 = str(num1)
55 | str11 = str11.replace("|", "")
56 | str11 = str11.replace("\n", "")
57 | str11 = str11.lstrip()
58 | str11 = str11.rstrip()
59 | str11 = str(str11)
60 | if (
61 | (" " in str11)
62 | or (")" in str11)
63 | or ("(" in str11)
64 | or ("<" in str11)
65 | or (">" in str11)
66 | ):
67 | print("Space / Paranthesis String : %s" % str11)
68 | else:
69 | with open(corpdir + "/seed-globals{0}".format(n), "w") as file:
70 | file.write(str11)
71 | print(
72 | "Extracting : %s"
73 | % str11
74 | )
75 | n = n + 1
76 |
77 |
78 | def main():
79 | args = parse_args()
80 | ensure_dir(args.corpdir)
81 | do_string_analysis(args.corpdir, args.infile)
82 |
83 |
84 | if __name__ == "__main__":
85 | main()
86 |
--------------------------------------------------------------------------------
/run.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import os
3 | import string
4 | import binascii
5 | import codecs
6 | import errno
7 | import struct
8 | import argparse
9 | import shutil
10 | import subprocess
11 |
12 | from binascii import unhexlify
13 |
14 |
15 | def ensure_dir(dir):
16 | try:
17 | os.makedirs(dir)
18 | except OSError as e:
19 | if e.errno != errno.EEXIST:
20 | raise
21 |
22 |
23 | def parse_args():
24 | parser = argparse.ArgumentParser(
25 | description=(
26 | "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project --------------------------------------------------------------------------- Example usage : python3 thisfile.py outdir str.txt"
27 | )
28 | )
29 |
30 | # parser.add_argument("tokenpath",
31 | # help="Destination directory for tokens")
32 | parser.add_argument("cur", help="Current Path")
33 | parser.add_argument("db", help="CodeQL database Path")
34 | parser.add_argument("tokenpath", help="Destination directory for tokens")
35 |
36 | return parser.parse_args()
37 |
38 |
39 | def static_analysis(file, file2, cur, db):
40 | with open(cur + "/" + file, "w") as f:
41 | print(cur + "/" + file)
42 | stream = os.popen("codeql query run " + cur + "/" + file2 + " -d " + db)
43 | output = stream.read()
44 | f.write(output)
45 | f.close()
46 |
47 |
48 | def copy_tokens(cur, tokenpath):
49 | subprocess.call(
50 | ["mv " + cur + "/" + "arrlits/*" + " " + cur + "/" + tokenpath + "/."],
51 | shell=True,
52 | )
53 |
54 | subprocess.call(
55 | ["mv " + cur + "/" + "globals/*" + " " + cur + "/" + tokenpath + "/."],
56 | shell=True,
57 | )
58 | subprocess.call(
59 | ["mv " + cur + "/" + "locals/*" + " " + cur + "/" + tokenpath + "/."],
60 | shell=True,
61 | )
62 | subprocess.call(
63 | ["mv " + cur + "/" + "magics/*" + " " + cur + "/" + tokenpath + "/."], shell=True
64 | )
65 | subprocess.call(
66 | ["mv " + cur + "/" + "memcmp-vals/*" + " " + cur + "/" + tokenpath + "/."],
67 | shell=True,
68 | )
69 | subprocess.call(
70 | ["rm -rf strcmp-strs memcmp-strs strncmp-strs lits strtool-strs"], shell=True
71 | )
72 | subprocess.call(["rm *.out"], shell=True)
73 | subprocess.call(["find " + tokenpath + " -size 0 -delete"], shell=True)
74 |
75 |
76 | def codeql_analysis(cur, db):
77 | print("codeql analysis func")
78 | static_analysis("arrlits.out", "array-literals.ql", cur, db)
79 | static_analysis("magics.out", "magic-values.ql", cur, db)
80 | static_analysis("memcmpvals.out", "memcmpvals.ql", cur, db)
81 | static_analysis("regex.out", "regex-values.ql", cur, db)
82 | static_analysis("strcmpvals.out", "strcmpvals.ql", cur, db)
83 | static_analysis("globals.out", "Global-values.ql", cur, db)
84 | static_analysis("strstr.out", "strstrvals.ql", cur, db)
85 | static_analysis("locals.out", "local-variables.ql", cur, db)
86 |
87 |
88 | start_fd(0, cur)
89 |
90 |
91 | def start_fd
92 | (tokenpath, cur):
93 | print("At start func")
94 | command = ["python3", cur + "/array-literals.py", cur + "/arrlits/.", cur + "/arrlits.out"]
95 | worker1 = subprocess.Popen(command)
96 | print(worker1.communicate())
97 |
98 | command1 = [
99 | "python3",
100 | cur + "/Global-values.py",
101 | cur + "/globals/",
102 | cur + "/globals.out",
103 | ]
104 | worker2 = subprocess.Popen(command1)
105 | print(worker2.communicate())
106 |
107 | command2 = [
108 | "python3",
109 | cur + "/local-variables.py",
110 | cur + "/locals/",
111 | cur + "/locals.out",
112 | ]
113 | worker3 = subprocess.Popen(command2)
114 | print(worker3.communicate())
115 |
116 | command5 = [
117 | "python3",
118 | cur + "/magic-values.py",
119 | cur + "/magics/",
120 | cur + "/magics.out",
121 | ]
122 | worker6 = subprocess.Popen(command5)
123 | print(worker6.communicate())
124 |
125 | command8 = [
126 | "python3",
127 | cur + "/memcmpvals.py",
128 | cur + "/memcmpvals/",
129 | cur + "/memcmpvals.out",
130 | ]
131 | worker9 = subprocess.Popen(command8)
132 | print(worker9.communicate())
133 |
134 | command9 = [
135 | "python3",
136 | cur + "/regex-values.py",
137 | cur + "/regexvals/",
138 | cur + "/regex.out",
139 | ]
140 | worker7 = subprocess.Popen(command9)
141 | print(worker7.communicate())
142 |
143 | command10 = [
144 | "python3",
145 | cur + "/strcmpvals.py",
146 | cur + "/strcmpvals/",
147 | cur + "/strcmpvals.out",
148 | ]
149 | worker8 = subprocess.Popen(command8)
150 | print(worker8.communicate())
151 |
152 | command11 = [
153 | "python3",
154 | cur + "/strstrvals.py",
155 | cur + "/strstrvals/",
156 | cur + "/strstr.out",
157 | ]
158 | worker10 = subprocess.Popen(command11)
159 | print(worker10.communicate())
160 |
161 |
162 |
163 | def main():
164 | args = parse_args()
165 | ensure_dir(args.tokenpath)
166 | codeql_analysis(args.cur, args.db)
167 | copy_tokens(args.cur, args.tokenpath)
168 |
169 |
170 |
171 | if __name__ == "__main__":
172 | main()
173 |
--------------------------------------------------------------------------------
/test-data/php_php-fuzz-parser_ranking.svg:
--------------------------------------------------------------------------------
1 |
2 |
4 |
5 |
1186 |
--------------------------------------------------------------------------------
/test-data/libpcap_fuzz_both_ranking.svg:
--------------------------------------------------------------------------------
1 |
2 |
4 |
5 |
1239 |
--------------------------------------------------------------------------------
/test-data/freetype2-2017_ranking.svg:
--------------------------------------------------------------------------------
1 |
2 |
4 |
5 |
1253 |
--------------------------------------------------------------------------------
/test-data/libxml2-v2.9.2_ranking.svg:
--------------------------------------------------------------------------------
1 |
2 |
4 |
5 |
1274 |
--------------------------------------------------------------------------------