
heretic
Fully automatic censorship removal for language models

Fully automatic censorship removal for language models

LLM-powered agent that autonomously fixes GitHub issues, finds cybersecurity vulnerabilities, and solves CTF challenges using configurable tool-use…

Automated Penetration Testing Agentic Framework Powered by Large Language Models

8 Lessons, Kick-start Your Cybersecurity Learning.


A curated knowledge base to build, run and mature a SOC (including CSIRT).

Source code about machine learning and security.

Curated systematic literature review of 756+ papers on LLM applications in cybersecurity, covering threat intelligence, vulnerability detection,…

reverse engineering Gemini's SynthID detection

A curated list of useful resources that cover Offensive AI.

The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers…

Interpretability and explainability of data and machine learning models

Curated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Research runtime for differentiable neural computers, GPU-based CPU emulation, and program synthesis. Features neural ALU, constant-time crypto, JEPA…

An Open-Source Package for Textual Adversarial Attack.

Standardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…

A collection of real-world threat model examples across various technologies, providing practical insights into identifying and mitigating security…