{"data":{"id":"85a321ed-7ca2-4da4-90c4-93ce22003cb8","title":"Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models","summary":"This research proposes bounded continuation analysis (BCA), which models autoregressive generation as a stochastic process over token prefixes and computes the finite-horizon probability that generation reaches a harmful continuation. The authors argue that attack success rate misses harmful paths hidden beneath sampled refusals, and that BCA can distinguish models with identical measured ASR. Across four instruction-tuned LLMs and 100 JailbreakBench behaviors, they report that BCA quantifies hidden harmful behavior and guides red teaming.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.22754v1","publishedAt":"2026-10-15T23:45:21.000Z","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":"2026-10-15T23:45:21.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}