oss-fuzz-gen and ps-fuzz
These are complements: OSS-Fuzz-Gen uses LLMs to generate fuzzing test cases for finding vulnerabilities in open-source software, while PS-Fuzz uses fuzzing techniques to test the robustness of LLM system prompts themselves—addressing security from opposite directions in the AI+security stack.
About oss-fuzz-gen
google/oss-fuzz-gen
LLM powered fuzzing via OSS-Fuzz.
Generates fuzz targets across C/C++, Java, and Python by prompting multiple LLMs (Vertex AI, Gemini, GPT-4) to synthesize harnesses, then evaluates them against OSS-Fuzz infrastructure using metrics like compilability, crash detection, and coverage gain versus human-written targets. The framework discovered 30+ real vulnerabilities including CVE-2024-9143 in OpenSSL, demonstrating LLM-generated targets can achieve up to 29% additional line coverage on production projects.
About ps-fuzz
prompt-security/ps-fuzz
Make your GenAI Apps Safe & Secure :rocket: Test & harden your system prompt
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work