
Guardrails
Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

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

CTI Cyber Threat Intelligence OSINT Dark Web Deep Web Research. Ransomware gang information gathering tool.

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

AI-curated blocklist of 3,000,000+ domains for blocking ads, trackers, malware, and cryptojacking. Integrates with hosts files, Pi-hole, and browser…

Privacy testing library for deep learning systems, enabling assessment of susceptibility to membership inference, model extraction, and model…

Plugin for Binary Ninja that integrates local Ollama models to rename functions and variables in decompiled HLIL code, preserving privacy by keeping…

This project (PoC for now, and part of Shit Bucket) involves face detection, face recognition and adversarial input to protect avatars