FuzzyAI
Red teaming automation
Automated LLM fuzzing tool from CyberArk Labs that runs a library of jailbreak and manipulation techniques (ArtPrompt, many-shot, taxonomy, persuasion and others) against cloud or local models to find guardrail weaknesses. For red teams and developers hardening models.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.