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

본문 미리보기

arXiv:2610.19005v1 Announce Type: new Abstract: 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 u