{"data":{"id":"91d59f1b-b44c-4699-be74-c77d6234a2d8","title":"CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn Jailbreak","summary":"CoFiBreak is a coarse-to-fine diversity reward for Group Relative Policy Optimization (GRPO) that trains an attacker LLM to produce more varied multi-turn jailbreaks. The coarse reward favors strategies underrepresented within each GRPO group, and the fine reward discourages reuse of the same personas, framings, and output formats. Against Llama3.1-8B-Instruct on HarmBench it finds 1.6-2.0x as many distinct successful fine-grained strategies as the strongest baseline, and it reaches 98.8% ASR@10 on AdvBench. The attacks transfer to unseen frontier models, reaching 71.0% ASR@10 on AdvBench against Claude-Opus-4.6.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.40926v1","publishedAt":"2026-10-29T19:51:36.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Meta","Anthropic"],"affectedVendorsRaw":["Llama3.1-8B-Instruct","Claude-Opus-4.6","HarmBench","AdvBench"],"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":"2026-10-29T19:51:36.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}