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

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

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

Adversary Emulation Framework

Clusters and elements to attach to MISP events or attributes (like threat actors)

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

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

An alignment auditing agent capable of quickly exploring alignment hypothesis

Bypass llm guardrails by confusing it with fabricated tool output.

Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing,…

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

Automated Adversary Emulation Platform

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

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

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

CVE-2026-6765, Test only FormAutofill handlers exposed in Firefox

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

Deterministic memory-poisoning / prompt-injection measurement axis — CoSnitch (CVE-2026-24301) anchored. Inspect scorer, signed receipts.…

Proof-of-concept exploit for CVE-2026-44578 that reproduces the vulnerable condition, enabling security researchers to validate affected systems and…