AutoPatchBench

Meta benchmark for AI repair of fuzzing-found C and C++ vulnerabilities.

Records citing AutoPatchBench

Apr 29, 2025
Meta releases AutoPatchBench to test AI repair of fuzzing-found C/C++ vulnerabilities
DefenseBenchmarkMeta

Meta introduced AutoPatchBench, part of CyberSecEval 4, with 136 fuzzing-identified C/C++ vulnerabilities and verified fixes, plus a 113-case Lite subset with single-function root causes. Patches are checked by build and crash reproduction, then fuzzing and white-box differential testing; Meta's reference agent generated crash-stopping patches in about 60% of cases, but only 5-11% passed the stricter checks.