oss-fuzz-gen and LegoFuzz
These are ecosystem siblings—OSS-Fuzz-Gen is a general-purpose LLM-guided fuzzer generator that integrates with Google's OSS-Fuzz infrastructure, while LegoFuzz is a specialized LLM-based fuzzing framework purpose-built for compiler testing, allowing them to coexist in the same category while serving distinct fuzzing domains.
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 LegoFuzz
cuhk-s3/LegoFuzz
An LLM-based fuzzing framework for C compilers testing.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work