FuzzyAI
StaleDescription
An automated LLM fuzzing tool by CyberArk that helps developers and security researchers identify and mitigate jailbreak vulnerabilities in LLM APIs with multiple attack vectors.
Related Projects
AI LLM Red Team Handbook
256 · Python
AI and LLM Red Team Field Manual and Consultant's Handbook, systematically covering red team assessment methodologies, attack techniques, and defense strategies.
red-teamhandbookllm-security +2
EasyJailbreak
851 · Python
An easy-to-use Python framework for generating adversarial jailbreak prompts, helping researchers systematically evaluate LLM safety defenses with multiple attack method combinations.
jailbreakadversarialllm-safety +2
0DIN Sidekick
27 · JavaScript
Firefox/Chromium extension for AI security researchers that streamlines LLM jailbreak testing and vulnerability discovery across multiple providers.
ai-safetyred-teamingjailbreak +2
AIGoat
53 · JavaScript
Open-source AI security playground for LLM red teaming with hands-on labs covering the full OWASP LLM Top 10 with progressive defenses.
ai-safetyred-teamingowasp +2