{"data":{"id":"b8d2579b-b0a4-409e-a4a4-6d91fc8cbca2","title":"Diagnose Before You Refine: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak Attacks","summary":"Jailbreak attacks on LLMs normally need many queries to refine adversarial prompts. This paper proposes JSB, a query-based framework that uses multi-dimensional probabilistic judge feedback, continuous jailbreak scoring, strategy switching and best-state reseeding to guide prompt optimization. Under a budget of only 10 target-model queries, JSB reaches an average HarmBench attack success rate of 89.8% across ten open-source settings, and the authors report that existing filtering mechanisms show limitations against it.","solution":"The source suggests the potential of Jev-based output filtering as a defense, but does not state a fix, patch, configuration change or workaround as a mitigation. N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.19971v1","publishedAt":"2026-10-14T10:55:17.000Z","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":"2026-10-14T10:55:17.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}