Metraipolis › archive › dc_8aac3fed71a6
SecureVibe: Making Vibe Coding More Secure — arXiv:2609.38606
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38606
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:14:19.266Z
- SHA-256 of the archived text
5a7ca44dc9f2d506916a4925962be4dab1ad83e669826dff9a9609d52b995372- Stable URL of this page
https://metraipolis.com/documento/dc_8aac3fed71a6
How to cite
SecureVibe: Making Vibe Coding More Secure — arXiv:2609.38606 — arXiv (en), https://arxiv.org/abs/2609.38606 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8aac3fed71a6 (Metraipolis archive dc_8aac3fed71a6, sha256 5a7ca44dc9f2d506916a4925962be4dab1ad83e669826dff9a9609d52b995372)
BibTeX
@misc{dc8aac3fed71a6,
title = {SecureVibe: Making Vibe Coding More Secure — arXiv:2609.38606},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38606},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8aac3fed71a6; sha256 5a7ca44dc9f2d506916a4925962be4dab1ad83e669826dff9a9609d52b995372},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38606. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. When investigating functionally correct but insecure solutions, we find that the insecure agent is less than half as likely to conduct effective planning and testing for the hidden security risks behind the functional requirements. Motivated by this, we develop SECUREVIBE, a training recipe that explicitly targets planning and testing for code security. SECUREVIBE constructs training signals around these security behaviors. It includes supervised fine-tuning on the security suite with 4 security tasks, and post-training methods, SECUREVIBE_rl and SECUREVIBE_hg, to enhance security capabilities from verifiable execution feedback and hint-based self-supervision. Our SECUREVIBE outperforms the baseline on two types of security coding tasks across 4 benchmarks. Specifically, SECUREVIBE improves the security pass@1 by 6.9 points on BaxBench. The gains extend to unseen CWE categories, with improvements of 11.5 points on SusVibes. Meanwhile, it also improves functionality pass@1 by 13.6 points on the security coding task SusVibes and 4.1 points on the generic coding task SWE-bench Verified. Further analysis offers two practical insights: (i) diversifying supervision across security planning, coding, and testing strengthens security behaviors more effectively than adding coding trajectories alone, and (ii) hint-guided supervision is particularly valuable when the agent's existing security capabilities are insufficient to learn effectively from outcome feedback. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL). Categorie arXiv: Cryptography and Security (cs.CR) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.38606 — 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 2026-10-07T12:44:51.936Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).