Metraipolis › archive › dc_b7e1ef61324f
Finding Vulnerabilities via LLM-Augmented Semantics-Aware Type-Checking — arXiv:2608.14533
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14533
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:29:35.776Z
- SHA-256 of the archived text
473246d9ef9afabcfc24be0ea04ff5ef7373df7c32e922868cf6dd105c10422d- Stable URL of this page
https://metraipolis.com/documento/dc_b7e1ef61324f
How to cite
Finding Vulnerabilities via LLM-Augmented Semantics-Aware Type-Checking — arXiv:2608.14533 — arXiv (en), https://arxiv.org/abs/2608.14533 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b7e1ef61324f (Metraipolis archive dc_b7e1ef61324f, sha256 473246d9ef9afabcfc24be0ea04ff5ef7373df7c32e922868cf6dd105c10422d)
BibTeX
@misc{dcb7e1ef61324f,
title = {Finding Vulnerabilities via LLM-Augmented Semantics-Aware Type-Checking — arXiv:2608.14533},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14533},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b7e1ef61324f; sha256 473246d9ef9afabcfc24be0ea04ff5ef7373df7c32e922868cf6dd105c10422d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14533. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vulnerability detection via static analysis traditionally relies on security experts encoding insecure coding patterns into algorithmic rules. However, this approach often focuses on syntactic patterns and overlooks deeper semantic information in the code, such as the meanings of variable and function names. As software systems grow more complex, modeling vulnerabilities using only syntactic rules becomes increasingly challenging. In this paper, we propose a semantics-aware approach to detecting software vulnerabilities. We present SETYPE, a semantics-aware type system that can be derived directly from source code based solely on the meanings of symbols and expressions in natural language. In the SETYPE type system, both type inference and checking are performed by Large Language Models (LLMs), and a failed type check indicates a potential vulnerability. We prototype PYSETYPE to demonstrate the feasibility of SETYPE for detecting vulnerabilities in Python web applications. Our evaluation on real-world applications achieves 87% detection precision and 88% detection accuracy. Using PYSETYPE, we identified 15 potential zero-day vulnerabilities, nine of which were confirmed by developers. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2608.14533 — 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 2026-10-19T02:25:38.622Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).