{"data":{"id":"7b46b9e3-5265-4ee7-a2e2-21d9bb20c0ac","title":"JailBound: FOL-Guided Jailbreak Evaluation for Exploring LLM Behavioral Boundaries","summary":"JailBound is a jailbreak evaluation framework that builds its benchmark automatically with a fine-tuned meta-attack generator and searches attacks with first-order loss (FOL)-guided dual-branch search. Tested on 46 LLMs from 13 model families, its High-Value Branch improves average ASR over a ZOL-only baseline by 5.1 and 4.9 percentage points across two settings. Its Safety-Sensitivity Branch shows higher behavioral flip rates than the High-Value Branch under local perturbations, indicating greater local sensitivity of judge-assigned safety labels.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security","safety"],"sourceUrl":"https://arxiv.org/abs/2611.07530v1","publishedAt":"2026-11-05T06:41:14.000Z","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":"2026-11-05T06:41:14.000Z","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"]}}