{"data":{"id":"9307f0e0-5902-4c83-a23a-8e6067749361","title":"Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning","summary":"Nullify is a training-free method for unlearning specific knowledge from LLMs at inference time, without weight updates. It applies steering vectors to redirect privacy-related activations away from memorized answers, while a null-space constraint keeps retained-query activations essentially unchanged. On TOFU and MUSE, it matches or surpasses established baselines in forget quality and achieves near-lossless preservation of model utility.","solution":"N/A -- no mitigation discussed in source.","labels":["research","privacy"],"sourceUrl":"https://arxiv.org/abs/2610.10655v1","publishedAt":"2026-10-07T16:24:07.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"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":"2026-10-07T16:24:07.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}