
chain-reactor
Generate Linux executables that simulate adversary behaviors and techniques for testing detection and response coverage. Consumes JSON for easy…

Generate Linux executables that simulate adversary behaviors and techniques for testing detection and response coverage. Consumes JSON for easy…

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Hands-on DEFCON workshop materials for killing and silencing EDR agents: lab setup, BYOVD, custom C/C++ evasion tooling, and reverse engineering.

Scripted framework for simulating over 50 MITRE ATT&CK techniques to test blue team detection capabilities. Includes Python scripts and a compiled…

A font-based deception tool for red teaming, security research, and whatever else.

Kill AV/EDR leveraging BYOVD attack

See adversary, do adversary: Simple execution of commands for defensive tuning/research (now with more ELF on the shelf)

A Python library for Secure and Explainable Machine Learning Documentation available @ https://secml.gitlab.io Follow us on Twitter @…

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

Fully automatic censorship removal for language models

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

A repo for jailbreaking various LLMs, mainly Claude

Automated Adversary Emulation Platform

Never ever ever use pixelation as a redaction technique

Source code about machine learning and security.

Interactive dashboards and libraries for responsible AI model debugging, covering error analysis, fairness, interpretability, counterfactuals, causal…

This repository contains detailed adversary simulation APT campaigns targeting various critical sectors. Each simulation includes custom tools, C2…

Interpretability and explainability of data and machine learning models