{"data":{"id":"18d35c35-b49b-422c-89be-a57ad228eb82","title":"Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes","summary":"Current LLM jailbreak evaluation relies on a binary success indicator, which hides how a prompt shapes the distribution of possible responses. The authors propose a continuous, context-conditioned risk landscape over first-token branches, estimated by fixing candidate openings and repeatedly sampling their continuations. Across multiple target models and jailbreak attacks, they find risky branches beneath apparently safe outputs, and attacks that are strongest before an adaptive defense are not always strongest after it reacts.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.38595v1","publishedAt":"2026-10-28T10:23:27.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"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":"2026-10-28T10:23:27.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.97,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}