{"data":{"id":"3f322c3b-3377-4c74-b02c-440113b91013","title":"Protecting Sensitive Knowledge Under LLM Unlearning: The Proxy Threat and a Superposition-Aware Defense","summary":"Researchers show that LLM unlearning can be exploited because entity representations overlap in shared parameter subspaces, a phenomenon called knowledge superposition. An attacker can submit a legitimate unlearning request for a removable proxy entity, which also removes a sensitive target entity that was never requested. The authors define this as the Proxy Unlearning Attack (PUA) and propose Superposition-Aware Unlearning Protection (SAUP), which detects at-risk entities before unlearning and restores affected entities afterward.","solution":"Proposed defense: Superposition-Aware Unlearning Protection (SAUP), applied to unlearning requests in two stages. Before unlearning, superposition detection estimates which sensitive entities the request puts at risk. After unlearning, SAUP decouples the shared representations and restores the affected entities while keeping the requested entities suppressed.","labels":["research","security"],"sourceUrl":"https://arxiv.org/abs/2611.15013v1","publishedAt":"2026-11-11T04:10:32.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"low","attackType":["other"],"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":"2026-11-11T04:10:32.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}