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.

Related items

• InfoBuilding Trust into Enterprise AI Agents: Cisco AI Defense and Workday Agent PassportSimilar attack · Cisco AI Blog
• InfoPolarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial FramingSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoABench: Adversarily Benchmarking Large Language Models across Taxonomized ValuesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoGlobal Security Blind Spots: Translation as a Safety Bypass in Low-Resource LanguagesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoSafety Mid-Training: Internalizing LLM Safety as a Foundational CapabilitySimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)