{"data":{"id":"b66a6d8e-ddfe-4c57-a6fc-5f8a83a2d736","title":"Harmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language Models","summary":"The paper shows that a harmful response generated for a query can serve as a jailbreak template for diffusion large language models (dLLMs). Masking a subset of its tokens induces the dLLM to reconstruct the harmful content. The authors propose RMT-Jailbreak, which transfers existing autoregressive (AR) jailbreak attacks to dLLMs by converting AR-generated harmful responses into high-mask-ratio templates. Experiments across multiple AR jailbreak methods and target dLLMs show strong cross-paradigm transferability.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.31331v2","publishedAt":"2026-10-22T14:20:36.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["diffusion large language models (dLLMs)"],"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":"2026-10-22T14:20:36.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}