pip install numpy scikit-learnimport base64
import re
import json
import numpy as np
from sklearn.ensemble import RandomForestClassifier
import argparse
hash_length_map = {
32: ["MD5 (128-bit)", "RIPEMD-128 (128-bit)"],
40: ["SHA-1 (160-bit)", "RIPEMD-160 (160-bit)"],
56: ["SHA-224 (224-bit)", "SHA3-224 (224-bit)"],
64: ["SHA-256 (256-bit)", "BLAKE2b (256-bit)", "BLAKE2s (256-bit)", "RIPEMD-256 (256-bit)", "SHA3-256 (256-bit)"]...
pip install numpy scikit-learnimport base64
import re
import json
import numpy as np
from sklearn.ensemble import RandomForestClassifier
import argparse
hash_length_map = {
32: ["MD5 (128-bit)", "RIPEMD-128 (128-bit)"],
40: ["SHA-1 (160-bit)", "RIPEMD-160 (160-bit)"],
56: ["SHA-224 (224-bit)", "SHA3-224 (224-bit)"],
64: ["SHA-256 (256-bit)", "BLAKE2b (256-bit)", "BLAKE2s (256-bit)", "RIPEMD-256 (256-bit)", "SHA3-256 (256-bit)"],
96: ["SHA-384 (384-bit)", "SHA3-384 (384-bit)"],
128: ["SHA-512 (512-bit)", "SHA3-512 (512-bit)", "RIPEMD-320 (320-bit)"],
43: ["Base64 (32-byte input)", "MD5 Base64 (128-bit)"],
56: ["Base64 (40-byte input)", "SHA-1 Base64 (160-bit)"],
88: ["Base64 (64-byte input)", "SHA-256 Base64 (256-bit)"],
120: ["Base64 (96-byte input)", "SHA-384 Base64 (384-bit)"],
172: ["Base64 (128-byte input)", "SHA-512 Base64 (512-bit)"]
}
X_train = np.array([
[32], [40], [56], [64], [96], [128], [43], [56], [88], [120], [172]
])
y_train = [
"MD5 (128-bit), RIPEMD-128 (128-bit)",
"SHA-1 (160-bit), RIPEMD-160 (160-bit)",
"SHA-224 (224-bit), SHA3-224 (224-bit)",
"SHA-256 (256-bit), BLAKE2b (256-bit), BLAKE2s (256-bit), RIPEMD-256 (256-bit), SHA3-256 (256-bit)",
"SHA-384 (384-bit), SHA3-384 (384-bit)",
"SHA-512 (512-bit), SHA3-512 (512-bit), RIPEMD-320 (320-bit)",
"Base64 (32-byte input), MD5 Base64 (128-bit)",
"Base64 (40-byte input), SHA-1 Base64 (160-bit)",
"Base64 (64-byte input), SHA-256 Base64 (256-bit)",
"Base64 (96-byte input), SHA-384 Base64 (384-bit)",
"Base64 (128-byte input), SHA-512 Base64 (512-bit)"
]
model = RandomForestClassifier(n_estimators=100)
model.fit(X_train, y_train)
def is_base64(s):
try:
if isinstance(s, str):
s_bytes = s.encode('ascii')
elif isinstance(s, bytes):
s_bytes = s
else:
return False
return base64.b64encode(base64.b64decode(s_bytes)).decode('ascii') == s
except Exception:
return False
def identify_hash_algorithm(hash_value):
length = len(hash_value)
if re.fullmatch(r'[0-9a-fA-F]+', hash_value):
format_type = "Hex"
elif is_base64(hash_value):
format_type = "Base64"
else:
format_type = "Unknown"
if format_type == "Hex":
if length in hash_length_map:
return ", ".join(hash_length_map[length]), None
else:
prediction = model.predict([[length]])[0]
return prediction, None
elif format_type == "Base64":
decoded_hash = base64.b64decode(hash_value)
decoded_content = decoded_hash.decode('utf-8', 'ignore')
length = len(decoded_hash) * 2
if length in hash_length_map:
return f"Base64 encoded hash detected. Possible algorithms: {', '.join(hash_length_map[length])}", decoded_content
else:
prediction = model.predict([[length]])[0]
return f"Base64 encoded hash detected. Possible algorithms: {prediction}", decoded_content
else:
return "Unknown or Unsupported Hash Algorithm", None
def compare_with_known_hashes(hash_value):
known_hashes = {
"5d41402abc4b2a76b9719d911017c592": "hello (MD5)",
"2cf24dba5fb0a30e26e83b2ac5b9e29e1b161e5c": "hello (SHA-1)",
"b94d27b9934d3e08a52e52d7da7dabfa2cfdd92d": "hello (SHA-224)",
"aGVsbG8=": "hello (Base64)"
}
return known_hashes.get(hash_value, "No match found")
def process_hashes(hashes):
results = {}
for hash_value in hashes:
identified_algorithm, decoded_content = identify_hash_algorithm(hash_value)
known_hash_match = compare_with_known_hashes(hash_value)
results[hash_value] = {
"identified_algorithm": identified_algorithm,
"decoded_content": decoded_content,
"known_hash_match": known_hash_match
}
return results
def save_report(results, filename='report.json'):
with open(filename, 'w') as file:
json.dump(results, file, indent=4)
print(f"Report saved to {filename}")
def main():
parser = argparse.ArgumentParser(description="Hash Algorithm Identifier CLI")
parser.add_argument('hashes', nargs='*', help="Hashes to identify")
parser.add_argument('-f', '--file', help="File containing hashes to identify")
parser.add_argument('-o', '--output', help="Output file for the report", default='report.json')
args = parser.parse_args()
hashes = args.hashes
if args.file:
try:
with open(args.file, 'r') as file:
hashes.extend([line.strip() for line in file])
except FileNotFoundError:
print("File not found.")
return
if not hashes:
print("No hashes provided.")
return
results = process_hashes(hashes)
for hash_value, result in results.items():
print(f"Hash: {hash_value} -> Identified: {result['identified_algorithm']}, Known Match: {result['known_hash_match']}")
if result['decoded_content']:
print(f"Decoded Content: {result['decoded_content']}")
save_report(results, args.output)
if __name__ == "__main__":
main()"736db6737d78876dba6f9e36775db56b" :
