Aug 16, 2023
Google reports LLM-written fuzz targets raise OSS-Fuzz code coverage in early experiments
Google's open source security team reports an experiment connecting OSS-Fuzz to an LLM that writes new fuzz targets for under-fuzzed code and revises them when they fail to compile. Google reports coverage gains of 1.5% to 31% across sample projects, and that an LLM-generated target rediscovered an already-known OpenSSL vulnerability in code that previously lacked fuzzing coverage.