AIJon: Automated Generation of Annotations for Fuzzing

Abstract

AIJon uses LLMs to generate IJON-style annotations that guide fuzzers toward deeper program states without requiring human domain experts. Evaluated on the Magma benchmark with AFL++, LLM-generated annotations perform comparably to human-written ones.

Publication
arXiv preprint arXiv:2609.18457
Hulin Wang
Hulin Wang
Ph.D. Candidate · LLM Agents for Vulnerability Discovery & Repair

Ph.D. candidate at ASU SEFCOM building LLM agents that find and fix real-world software vulnerabilities.