Metraipolis › archive › dc_f36f23ef2c80
AIJon: Automated Generation of Annotations for Fuzzing — arXiv:2609.18457
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18457
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:31:38.231Z
- SHA-256 of the archived text
d2860082c1061efee7c0cd4d6c64870f1264af792110c8cac1f27334586516f4- Stable URL of this page
https://metraipolis.com/documento/dc_f36f23ef2c80
How to cite
AIJon: Automated Generation of Annotations for Fuzzing — arXiv:2609.18457 — arXiv (en), https://arxiv.org/abs/2609.18457 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f36f23ef2c80 (Metraipolis archive dc_f36f23ef2c80, sha256 d2860082c1061efee7c0cd4d6c64870f1264af792110c8cac1f27334586516f4)
BibTeX
@misc{dcf36f23ef2c80,
title = {AIJon: Automated Generation of Annotations for Fuzzing — arXiv:2609.18457},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18457},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f36f23ef2c80; sha256 d2860082c1061efee7c0cd4d6c64870f1264af792110c8cac1f27334586516f4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18457. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern fuzzers use code coverage as feedback to guide their exploration which has proven to be an effective strategy for driving exploration. However, this strategy overlooks inputs that may be interesting to the target program even without uncovering new code paths. Fortunately, prior research has shown that annotations generated by human domain experts can provide additional feedback, guiding the fuzzer towards interesting parts of the program. In this paper, we replicate experiments presented in IJON and extend them to real-world vulnerability detection at scale. To mitigate the scalability challenge, imposed by the need for human domain expertise, we propose utilizing LLMs to automatically generate annotations. We demonstrate the applicability of LLMs for this purpose and observe that LLMs can generate annotations that perform comparably to human-generated annotations. Motivated by this finding, we design AIJON, a system that leverages LLMs to automatically generate IJON-style annotations. We evaluate AIJON on the Magma benchmark and surprisingly observe that annotation-based fuzzing does not perform strictly better than AFL++. We conduct several experiments to identify the cause of our results and identify key insights regarding the impact of annotations on fuzzing campaigns, including their effect on the energy distribution of the fuzzer. Notably, we observe that LLMs can generate annotations that achieve comparable results to human generated ones, thus opening the door for future research to perform further studies on the impact of annotations at scale. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.18457 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:56:52.850Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).