{"data":{"id":"21ef529b-bd86-4915-95d7-0737ed8f6fea","title":"CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat","summary":"CyberArena is a benchmark that pits two AI agents against each other in live, symmetric attack-and-defense matches inside isolated sandboxes, with services that change over time. Across 466 matches involving 12 frontier LLM agents and 40 challenges, it separates model capabilities that single-agent static benchmarks fail to distinguish. The authors report that defenders often patch one flaw while missing the next, and that stronger agents plant backdoors for later rounds.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.19005v1","publishedAt":"2026-10-13T18:05:26.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-13T18:05:26.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":null,"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}