Metraipolis › archive › dc_e512f29865e2

LLM-Assisted Automatic Security Proofs for Cryptographic Protocols: How Far Are We? — arXiv:2609.35434

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35434
License (as archived)
CC0-1.0
Archived
2026-10-07T22:34:56.961Z
SHA-256 of the archived text
0c3a0a7273696dfc4400cf5c6e15d67073403c78b3cd88cfe7f75c8b5ca7593c
Stable URL of this page
https://metraipolis.com/documento/dc_e512f29865e2

How to cite

LLM-Assisted Automatic Security Proofs for Cryptographic Protocols: How Far Are We? — arXiv:2609.35434 — arXiv (en), https://arxiv.org/abs/2609.35434 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e512f29865e2 (Metraipolis archive dc_e512f29865e2, sha256 0c3a0a7273696dfc4400cf5c6e15d67073403c78b3cd88cfe7f75c8b5ca7593c)
BibTeX
@misc{dce512f29865e2,
  title = {LLM-Assisted Automatic Security Proofs for Cryptographic Protocols: How Far Are We? — arXiv:2609.35434},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35434},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e512f29865e2; sha256 0c3a0a7273696dfc4400cf5c6e15d67073403c78b3cd88cfe7f75c8b5ca7593c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35434. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have shown strong potential for assisting software and security analysis tasks, yet their effectiveness in cryptographic symbolic protocol verification remains insufficiently understood. In this paper, we conduct the first systematic evaluation of the capability of state-of-the-art LLMs in cryptographic symbolic protocol verification. To quantify this capability, we propose \textsc{CRoST} (Coverage Rate of Solve Tree), a proof-based metric derived from the verifier's proof skeleton that measures the similarity between generated lemmas and reference lemmas. We then establish the rationale of \textsc{CRoST} through both theoretical analysis and empirical validation. The evaluation results show that state-of-the-art models achieve 38.82\% coverage on average, with 14.4\% of generated lemmas exceeding 80\% coverage, indicating that LLMs can already generate useful lemmas to a certain extent. However, they still exhibit non-trivial failure modes on complex multi-phase protocols, show diminishing returns under naive scaling, and incur substantial verification overhead. These findings clarify the practical potential and limitations of LLMs for protocol verification and motivate future work on complex real-world protocols.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.35434 — 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 2026-10-07T22:13:03.749Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).