Metraipolis › archive › dc_4e5e2bc91006

JevVibe: Efficient Classification-Guided Secure Code Generation — arXiv:2609.34963

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34963
License (as archived)
CC0-1.0
Archived
2026-10-07T21:03:05.815Z
SHA-256 of the archived text
cb0cd502d8d9324df980753f8b75ce232abec74614c8b181e6e6ce4381082dc7
Stable URL of this page
https://metraipolis.com/documento/dc_4e5e2bc91006

How to cite

JevVibe: Efficient Classification-Guided Secure Code Generation — arXiv:2609.34963 — arXiv (en), https://arxiv.org/abs/2609.34963 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e5e2bc91006 (Metraipolis archive dc_4e5e2bc91006, sha256 cb0cd502d8d9324df980753f8b75ce232abec74614c8b181e6e6ce4381082dc7)
BibTeX
@misc{dc4e5e2bc91006,
  title = {JevVibe: Efficient Classification-Guided Secure Code Generation — arXiv:2609.34963},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34963},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e5e2bc91006; sha256 cb0cd502d8d9324df980753f8b75ce232abec74614c8b181e6e6ce4381082dc7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34963. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models can generate functionally correct code that still contains security weaknesses, motivating repair pipelines that first diagnose a weakness type before deciding how to fix it. The Common Weakness Enumeration (CWE) provides a standardized vocabulary for such diagnoses, but asking an autoregressive language model to generate a CWE label and extracting it from the response raises questions about output validity, speed, and cost, as well as accuracy. We evaluate Jev, a decision model that instead selects directly from a declared set of candidates and returns a probability for each, against six open-weight autoregressive models and a frontier proprietary model, GPT-5.6-Sol, on a controlled 50-way CWE classification task over 1,916 CyberSecEval benchmark examples. Jev outperforms all six open-weight baselines on every classification and ranking metric, while its comparison with GPT-5.6-Sol depends on the metric: GPT-5.6-Sol achieves higher Top-1 accuracy and Macro-F1, whereas Jev achieves higher Top-3 and Top-5 accuracy and a nearly identical MRR, at $6.27\times$ lower median API latency and $55.9\times$ lower estimated API cost. We further build JevVibe, a diagnosis-guided repair agent that uses predicted CWE labels to repair code generated by Qwen2.5-Coder-32B-Instruct. With Jev providing the diagnosis, the agent increases the detector-measured security pass rate from 63.5% before repair to 70.7%, compared with 66.1% for LLM-guided repair. These results show that JevVibe is effective at improving the security of generated code, with Jev providing reliable and efficient CWE classification.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34963 — 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 2026-10-07T20:29:03.200Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).