{"data":{"id":"a5144ff5-c722-4188-904c-d68b99f9dd68","title":"Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation","summary":"This research examines how jailbreak evaluation depends on the judge LLM, showing that swapping only the judge can change reported attack success rate by up to 82 percentage points. The authors introduce the semantic reconstruction game, a training-free evaluator that reconstructs the request a response answers and compares it against decoy requests, with abstention when neither matches. Across three off-the-shelf LLM judges it achieves the lowest mean error against human labels among the methods evaluated and reduces variation in reported ASR, prioritizing avoidance of false positives.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2610.19306v1","publishedAt":"2026-10-13T23:32:17.000Z","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":"2026-10-13T23:32:17.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}