cyberark/FuzzyAI
Automated LLM fuzzing tool that identifies jailbreak vulnerabilities and security weaknesses in LLM APIs.
Not currently ranked — collecting fresh signals.
star history
FuzzyAI is a security testing tool for language models that automatically probes LLM APIs to discover potential jailbreaks and security vulnerabilities. Developers and security researchers can use it to evaluate the robustness of their LLM deployments against adversarial prompt attacks. The tool operates by generating test cases and feeding them to target LLMs to detect failure modes in model safety responses.
Frequently asked
- What is cyberark/FuzzyAI?
- Automated LLM fuzzing tool that identifies jailbreak vulnerabilities and security weaknesses in LLM APIs.
- Is FuzzyAI open source?
- Yes — cyberark/FuzzyAI is open source, released under the Apache-2.0 license.
- What language is FuzzyAI written in?
- cyberark/FuzzyAI is primarily written in Jupyter Notebook.
- How popular is FuzzyAI?
- cyberark/FuzzyAI has 1.5k stars on GitHub.
- Where can I find FuzzyAI?
- cyberark/FuzzyAI is on GitHub at https://github.com/cyberark/FuzzyAI.