Python module for obfuscation classification in command line executions
Project description
Command Obfuscation Detection
This project currently only supports cmd.exe command obfuscation detection on Windows. In a previous iteration of this project, we used deep learning. Now, we have shifted the approach towards XGBoost instead.
- Blog post: https://medium.com/adobetech/using-deep-learning-to-better-detect-command-obfuscation-965b448973e0
- Pip package: https://pypi.org/project/obfuscation-detection/
Quick Installation
You can install our package through pip!
pip install obfuscation-detection
This is a basic usage of our package:
from obfuscation_detection import ObfuscationDetectionClassifier
model = ObfuscationDetectionClassifier()
commands = ['cmd.exe /c "echo Invoke-DOSfuscation"',
'cm%windir:~ -4, -3%.e^Xe,;^,/^C",;,S^Et ^^o^=fus^cat^ion&,;,^se^T ^ ^ ^B^=o^ke-D^OS&&,;,s^Et^^ d^=ec^ho I^nv&&,;,C^Al^l,;,^%^D%^%B%^%o^%"',
'cat /etc/passwd']
y = model.predict(commands)
y_prob = model.predict_proba(commands)
# 1 is obfuscated, 0 is non-obfuscated
print(y) # [0, 1, 0]
print(y_prob)
Usage
-
Install python dependencies:
pip install -r requirements.txt
-
For quick usage, give a .csv file with column
commands
and you can run the commands through the model:python obfuscation_detection/main.py --filename commands.csv
-
You can also write your own scripts to use the model class directly:
python obfuscation_detection/model.py
Contributing
Contributions are welcomed! Read the Contributing Guide for more information.
Licensing
This project is licensed under the Apache V2 License. See LICENSE for more information.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file obfuscation_detection-1.0.0.tar.gz
.
File metadata
- Download URL: obfuscation_detection-1.0.0.tar.gz
- Upload date:
- Size: 30.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
5dd63ea8102aea818de431ba39f6756927825aac1bde7c734d9ed8b0eb9b0fff
|
|
MD5 |
a6ff126f319cc9a50b2e6a827c14a697
|
|
BLAKE2b-256 |
9a4739b4131bc27ba4816387e910746fd52d0229549e08117e8678c780dc767c
|
File details
Details for the file obfuscation_detection-1.0.0-py3-none-any.whl
.
File metadata
- Download URL: obfuscation_detection-1.0.0-py3-none-any.whl
- Upload date:
- Size: 29.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
ffa5c2c2641775d34743732fa535715a4451ed9a7767f239de4e278885d8dded
|
|
MD5 |
f17b769adb4902ffbb2584c4e4cafafd
|
|
BLAKE2b-256 |
a8adc0a302eb8aaa29d4d4a9b28e0bdc16452749d539a06ee97be148fb085f3f
|