Metraipolis › archive › dc_62dc68beed5c
Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks — arXiv:2610.06584
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06584
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:46.265Z
- SHA-256 of the archived text
1e8fd5ecb25ea19ad7b83e27a25bbaa4e4bb3163f1813277c15195fbf822051a- Stable URL of this page
https://metraipolis.com/documento/dc_62dc68beed5c
How to cite
Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks — arXiv:2610.06584 — arXiv, https://arxiv.org/abs/2610.06584 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62dc68beed5c (Metraipolis archive dc_62dc68beed5c, sha256 1e8fd5ecb25ea19ad7b83e27a25bbaa4e4bb3163f1813277c15195fbf822051a)
BibTeX
@misc{dc62dc68beed5c,
title = {Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks — arXiv:2610.06584},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06584},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62dc68beed5c; sha256 1e8fd5ecb25ea19ad7b83e27a25bbaa4e4bb3163f1813277c15195fbf822051a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06584. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The release decision for frontier AI systems increasingly relies on cyber capability benchmarks, yet public vulnerability benchmarks can expose agents to previously published advisories, exploits, and fixes, making it difficult to distinguish prior exposure from capability on unseen vulnerabilities. We evaluate open-weight and proprietary AI models on exploit generation, vulnerability repair and subsequent attacks in five nonpublic software environments, including vulnerabilities we privately disclosed while they remained unpatched. Researcher-developed and reviewed deterministic graders, not LLM judges, determine task scores. Comparisons with 209 disclosed vulnerabilities and cryptographic challenges reveal substantial variation across systems and vulnerability types. Repair scores exceed attack scores in two nonpublic environments and fall below them in three. Passing an initial security test is also insufficient: another exploit succeeds in 92 of 524 non-independent defender test intervals after the initial exploit is stopped. These results motivate vulnerability-specific attack-repair comparisons and subsequent resistance tests. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.06584 — 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 2026-10-06T05:24:06.173Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).