{"data":{"id":"073cc802-f02d-4585-82a7-b11a55a36dcf","title":"Paired response final divergence signatures of jailbreak vulnerability in large language models","summary":"This paper introduces a paired response-final divergence framework that measures jailbreak-induced representational displacement between same-goal direct and jailbreak responses, using hidden states at the final generated token. Applied to 15 open-source LLMs across four alignment strategies and four attack types, it finds that Difference-in-Means refusal direction suppression shows the largest cross-model association with jailbreak amplification. Divergence–ΔASR correlation is attack-type-specific, strongest for authority framing (r = 0.836) and context manipulation (r = 0.712), and weak for roleplay attacks.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://doi.org/10.1007/s44163-026-02593-2","publishedAt":"2026-10-23T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Vicuna","LLaMA"],"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":"2026-10-23T00:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":["AML.T0054"]}}