{"data":{"id":"0cb9c518-a1ab-44fb-8592-3d59ced715e3","title":"Orthogonal Boundary Unlearning for Dual-Use Concepts in Large Language Models","summary":"Researchers propose Orthogonal Boundary Unlearning (OBU), a framework for removing hazardous operational capabilities, such as cyberwarfare exploitation and pathogen enhancement, from large language models while preserving benign dual-use knowledge. OBU restricts parameter updates to the orthogonal null space of a capability subspace extracted via singular value decomposition, and is realized as Projected LoRA or Closed-Form Weight Surgery. Tested on Gemma-3-4B, Qwen3.5-4B, SmolLM3-3B, and Granite-4.2-3B, the authors report strong concept separation, substantial mitigation of in-context priming attacks, and resistance to adversarial relearning without degrading benign competence.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.27490v1","publishedAt":"2026-10-20T02:09:21.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Gemma-3-4B","Qwen3.5-4B","SmolLM3-3B","Granite-4.2-3B"],"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":"2026-10-20T02:09:21.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}