{"data":{"id":"4acb54d2-73a8-4606-b2ff-0a12f6c160ef","title":"J-Anchor: Defending Against Prefill Attacks via J-Space Selective Refusal Restoration","summary":"This research paper studies how prefill jailbreaks cause safety-aligned language models to continue an unsafe assistant prefix. Using the Jacobian lens, the authors track harmfulness and refusal signals through prefilling and generation, and identify refusal-state erosion, where the refusal signal declines to the benign baseline by the end of the prefill while the harmfulness signal stays above it. They introduce J-Anchor, a training-free inference-time defense that selectively restores weakened refusal in J-space, which substantially reduces attack success under fixed and deep prefill attacks across model families while largely preserving benign behavior.","solution":"J-Anchor: a training-free inference-time defense that uses the model's pre-attack harmfulness and refusal signals as a request-specific anchor and selectively restores weakened refusal in J-space during prefilling and decoding.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.01342v1","publishedAt":"2026-10-31T23:19:05.000Z","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":"2026-10-31T23:19:05.000Z","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"]}}