
redthread
An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…


Adversary Emulation Framework

Automated Adversary Emulation Platform

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

Adversary simulation and Red teaming platform with AI

The exploit server for out-of-band findings. Point a target at a domain you own. Every HTTP request and every email it sends back lands in a…

Metasploit for machine learning.

AI / LLM Red Team Field Manual & Consultant’s Handbook

Playbook-based adversary simulation framework that compiles JSON-defined attack paths into position-independent shellcode payloads for validating…

Port of Cobalt Strike's Process Inject Kit

CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation

Advanced CVE-2023-44487 HTTP/2 Rapid Reset vulnerability exploitation framework. Features multi-connection concurrent attacks, adaptive rate control,…

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

Evaluation framework for studying LLM agents that automatically generate working exploits from vulnerability reports, bypassing modern security…

LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…