Koukyosyumei/AIJack
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
This tool helps machine learning engineers and data scientists evaluate the security and privacy risks of their AI models. It allows you to simulate various attacks like data poisoning or model inversion and test defenses such as differential privacy or homomorphic encryption. You input your existing AI models, and it outputs insights into their vulnerabilities and the effectiveness of security measures.
422 stars.
Use this if you are responsible for deploying AI systems and need to proactively assess and mitigate potential security and privacy threats before they become real-world problems.
Not ideal if you are looking for a general-purpose machine learning library or a tool to build AI models from scratch.
Stars
422
Forks
67
Language
C++
License
Apache-2.0
Category
Last pushed
Jan 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Koukyosyumei/AIJack"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
google/scaaml
SCAAML: Side Channel Attacks Assisted with Machine Learning
pralab/secml
A Python library for Secure and Explainable Machine Learning
AI-SDC/SACRO-ML
Collection of tools and resources for managing the statistical disclosure control of trained...
liuyugeng/ML-Doctor
Code for ML Doctor
oss-slu/mithridatium
Mithridatium is a research-driven project aimed at detecting backdoors and data poisoning in...