EasyJailbreak
NormalDescription
An easy-to-use Python framework for generating adversarial jailbreak prompts, helping researchers systematically evaluate LLM safety defenses with multiple attack method combinations.
Related Projects
FuzzyAI
1.4k · Jupyter Notebook
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.
fuzzingllm-securityjailbreak +2
AgentDojo
560 · Python
A dynamic environment by ETH Zurich to evaluate attacks and defenses for LLM agents, providing standardized benchmarks for measuring agent system security.
security-benchmarkagent-evaluationattack-defense +2
AI Red Teaming Playground Labs
1.9k · TypeScript
Microsoft's open-source AI red teaming playground labs with infrastructure for running AI red teaming trainings and hands-on security exercises.
red-teamtrainingsecurity +2
JailTrickBench
162 · Python
Bag of Tricks for benchmarking jailbreak attacks on LLMs. NeurIPS 2024 paper providing empirical tricks for LLM jailbreaking with standardized evaluation.
benchmarkjailbreakllm-safety +2