{"data":{"id":"7c620068-2e4b-4936-9274-cbe4d07bfc98","title":"Jailbreak Detection on Large Language Models via Contrastive Prototype Structures","summary":"Researchers propose JDPI, a jailbreak detection method that builds harmful and benign prototypes from binary safety labels and classifies inputs by relative prototype distance, avoiding a separate downstream classifier. Across four benchmarks, contrastive fine-tuning raises detection accuracy by 9.1-18.0 percentage points, and JDPI exceeds the released Llama Guard 3-8B baseline by 0.173-0.310 in ROC-AUC with dataset-specific adaptation. In multi-turn replay, using accumulated user history yields higher conversation-level accuracy than using the current turn alone.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety","research"],"sourceUrl":"https://arxiv.org/abs/2611.24936v1","publishedAt":"2026-11-18T18:56:12.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Meta"],"affectedVendorsRaw":["Llama Guard 3-8B","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":"2026-11-18T18:56:12.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}