oss-fuzz-gen and LLMFuzzer
These are complements: OSS-Fuzz-Gen generates fuzzing inputs for traditional software using LLMs, while LLMFuzzer uses fuzzing techniques to test the LLMs themselves, addressing different layers of the testing pipeline.
About oss-fuzz-gen
google/oss-fuzz-gen
LLM powered fuzzing via OSS-Fuzz.
This framework helps software security teams automate and enhance their fuzz testing efforts by using Large Language Models (LLMs) to generate new fuzz targets for C, C++, Java, and Python projects. It takes existing project code and an LLM as input, then outputs new fuzzing code and detailed reports on its effectiveness, including crash discovery and code coverage. This is intended for security engineers and quality assurance professionals focused on identifying vulnerabilities in open-source and proprietary software.
About LLMFuzzer
mnns/LLMFuzzer
🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. 🚀💥
This tool helps security enthusiasts and pentesters find vulnerabilities in applications that use Large Language Models (LLMs). It takes your LLM API endpoint and fuzzer configurations as input, then generates various malicious inputs to test the LLM's robustness and reveal security flaws in how your application interacts with the LLM. It's designed for cybersecurity researchers looking to stress-test AI systems.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work