Raideeen/Explainable-AI-malware-detection
Malware detection with added explanability of AI through saliency map on Android APK using PyTorch and Androguard.
This project helps security analysts and researchers understand why an AI model flags certain Android applications (APKs) as malicious. You provide a collection of Android APK files, and the tool uses a machine learning model to classify them. Critically, it then generates 'saliency maps'—visual explanations that highlight which parts of the APK's structure led to the detection, making the AI's decision process transparent.
No commits in the last 6 months.
Use this if you need to not only detect malware in Android APKs but also gain insight into the specific characteristics or patterns that the AI model identifies as indicators of malicious behavior.
Not ideal if you are looking for a plug-and-play solution for immediate, large-scale production malware detection without the need for detailed explainability or custom model training.
Stars
9
Forks
3
Language
Python
License
MIT
Category
Last pushed
Feb 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Raideeen/Explainable-AI-malware-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rednaga/APKiD
Android Application Identifier for Packers, Protectors, Obfuscators and Oddities - PEiD for Android
0xfke/Malware-Detection-and-Analysis-using-Machine-Learning
Malware🦠Detection and Analysis using Machine Learning (MDAML) is designed to provide users with...
rieck/malheur
A Tool for Automatic Analysis of Malware Behavior
AFAgarap/malware-classification
Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support...
Kiinitix/Malware-Detection-using-Machine-learning
Anomaly based Malware Detection using Machine Learning (PE and URL)