{"data":{"id":"e41f27ef-0b32-4824-9be5-32c1610d6e91","title":"Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security","summary":"The authors co-train attacker and defender populations of LoRA adapters over one frozen base model, using PRPO (Peer-Relative Policy Optimization), where rewards come from execution in isolated containers rather than static datasets. The resulting 7B diff reviewer reaches 64.8% balanced accuracy on four unseen applications in three untrained languages, 5.5 points above supervised security fine-tuning and 4.4 above a frozen Claude Opus 4.8 reviewer. The 9B repository agent recovers 23 of 172 held-out VulnGym advisories, against 10 after supervised fine-tuning.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.24896v1","publishedAt":"2026-10-17T22:36:09.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion","jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Claude Opus 4.8","GLM-5.2","WildGuard","mini-swe-agent"],"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":"2026-10-17T22:36:09.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}