HGFuzzer uses an LLM to generate harnesses, reachable seeds, and custom mutators for directed greybox fuzzing, and reports triggering 17/20 known vulnerabilities plus finding 9 new ones with CVE IDs.
CodeQL documentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Directed Greybox Fuzzing via Large Language Model
HGFuzzer uses an LLM to generate harnesses, reachable seeds, and custom mutators for directed greybox fuzzing, and reports triggering 17/20 known vulnerabilities plus finding 9 new ones with CVE IDs.