{"data":{"id":"4157f3a5-165b-49af-ac87-4468a3cab5c5","title":"The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision","summary":"The paper introduces SADDER, an extension of the Safety-Aware Denoiser (SAD) for text diffusion models. SADDER uses an embedding-space safety signal to gate which token positions SAD's update rule modifies, and derives new position-wise target distributions so the modified denoiser stays exact. Tested on Masked Diffusion Language Models and Uniform-State Diffusion Models in unsafe continuation and jailbreak settings, it reportedly balances safety, generation quality and inference cost better than existing methods.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.17636v1","publishedAt":"2026-10-13T03:04:22.000Z","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":"2026-10-13T03:04:22.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}