
heretic
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

A privacy-first app that strips AI watermarks from content you own.

Adversary Emulation Framework

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

A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine…

Set of tools to assess and improve LLM security.

Never ever ever use pixelation as a redaction technique

Open-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…

Simple (relatively) things allowing you to dig a bit deeper than usual.

Empire is a post-exploitation and adversary emulation framework that is used to aid Red Teams and Penetration Testers.

Infection Monkey - An open-source adversary emulation platform

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Source code about machine learning and security.

Adversary simulation and Red teaming platform with AI

A curated list of useful resources that cover Offensive AI.

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

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in…

Improve your security and privacy by blocking ads, tracking and malware domains.