Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Guardrails, PII redaction, prompt-injection defense, interpretability and offensive/defensive AI security.
Signals: ai-safety, ai-security, guardrails, prompt-injection, jailbreak, llm-security, interpretability, explainable-ai
370 results
Universal and Transferable Attacks on Aligned Language Models
A Platform for Secure Analytics and Machine Learning
Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.
Explain & debug any blackbox machine learning model with a single line of code.
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.
Model extraction attacks on Machine-Learning-as-a-Service platforms.
Robust machine learning for responsible AI
No description
Metasploit for machine learning.
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
A collection of research papers and software related to explainability in graph machine learning.
GyoiThon is a growing penetration test tool using Machine Learning.
Interpretability and explainability of data and machine learning models
XAI - An eXplainability toolbox for machine learning
Algorithms for explaining machine learning models
Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.
No description
A curated list of awesome responsible machine learning resources.
Source code about machine learning and security.
Deep Learning Interpretability with Symbolic Regression
Deep learning based content moderation from text, audio, video & image input modalities.
This repository explores explainable deep learning models for financial fraud detection and anomaly analysis. It integrates Graph Neural Networks (GNNs), Autoencoders, and SHAP-based explainability to identify and interpret fraudulent behaviors in transactional data.
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
24,545 repositories in the index in total.
