{"data":{"id":"678cb861-877b-40ec-86c9-7467b3afa6fe","title":"Adversarial Self-Distillation","summary":"Adversarial Self-Distillation (ASD) is proposed as a defense against adversarial perturbations that bypass refusals in safety-aligned language models. The method has the model act as its own teacher on clean prompts, distilling refusal behavior to the same model under attack at the prefixes it visits, including compliant openings. ASD achieves lower attack success than state-of-the-art defenses with little loss in multiple-choice accuracy.","solution":"ASD: the model distills its own safe refusal behavior, given clean prompts, into its adversarially perturbed self at the prefixes it visits during on-policy sampling.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.38732v1","publishedAt":"2026-10-28T19:26:43.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak","model_evasion"],"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":"2026-10-28T19:26:43.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}