Metraipolis › archive › dc_e495d01aecc5

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat — arXiv:2610.19005

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19005
License (as archived)
CC0-1.0
Archived
2026-10-15T13:50:41.488Z
SHA-256 of the archived text
042d1b6750b55edf1e3fd4def6a70410985338a5af9a1787d62d85359b7a35ab
Stable URL of this page
https://metraipolis.com/documento/dc_e495d01aecc5

How to cite

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat — arXiv:2610.19005 — arXiv (en), https://arxiv.org/abs/2610.19005 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e495d01aecc5 (Metraipolis archive dc_e495d01aecc5, sha256 042d1b6750b55edf1e3fd4def6a70410985338a5af9a1787d62d85359b7a35ab)
BibTeX
@misc{dce495d01aecc5,
  title = {CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat — arXiv:2610.19005},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19005},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e495d01aecc5; sha256 042d1b6750b55edf1e3fd4def6a70410985338a5af9a1787d62d85359b7a35ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19005. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets. Real cyber operations, however, are dynamic and coupled: security postures constantly change as attackers and defenders adapt to each other in real time. Static benchmarks quickly saturate and miss an agent's ability to attack and defend simultaneously under live pressure. To address this gap, we present CyberArena, a dynamic, symmetric adversarial benchmark built around multi-round attack-and-defense combat. In isolated sandboxes, two agents compete under identical rules, acting concurrently as both attackers and defenders over continuously changing services. This converts static targets into evolving, semi-open challenges, directly testing an agent's speed and precision in discovering, exploiting, and patching vulnerabilities. To sustain the benchmark's longevity, an automated agentic pipeline continuously generates, reviews, and validates new environments. Furthermore, because pairwise contests are notoriously hard to quantify, we introduce a dynamical model that maps match dynamics into unified, multidimensional scores across offensive, defensive, and domain-specific capabilities. Evaluating 12 frontier LLM agents across 40 challenges in 466 matches, CyberArena separates model capabilities where single-agent baselines hit a ceiling. The trajectories read like a fight rather than an exam: defenders patch one hole and miss the next and certify repairs on stale evidence, while capable agents think a move ahead, planting backdoors for later rounds and, in one case, writing their own packet sniffer to watch the opponent. Beyond a benchmark, CyberArena serves as an adaptable, scalable experimental platform for future research on cybersecurity agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.19005 — 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 2026-10-15T13:48:35.445Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).