CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer

Computer Science > Cryptography and Security [Submitted on 19 Mar 2026] CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer Yue Zhao, Yujia Gong, Ruigang Liang, Shenchen Zhu, Kai Chen, Xuejing Yuan, Wangjun Zhang The widespread deployment of large language models (LLMs) calls for post-hoc methods that can flexibly adapt models to evolving safety requirements. Meanwhile, the rapidly expanding open-source LLM ecosystem has produced a diverse collection of models that already exhibit various safety-related functionalities. This motivates a shift from constructing safety functionality from scratch to reusing existing functionality from external models, thereby avoiding costly data collection and training procedures. In this paper, we present Cross-Model Neuron Transfer (CNT), a post-hoc method that reuses safety-oriented functionality by transferring a minimal subset of neurons from an open-source donor LLM to a target LLM. By operating at the neuron level, CNT enables modular function-level adaptation, supporting both function addition andfunction deletion. We evaluate CNT on seven popular LLMs across three representative applications: safety disalignment, alignment enhancement, and bias removal. Experimental results show that CNT achieves targeted safety-oriented functionality transfer with minimal performance degradation (less than 1% for most models), consistently outperforming five baselines, demonstrating its generality and practical effectiveness. Subjects: Cryptography and Security (cs.CR); Software Engineering (cs.SE) Cite as: arXiv:2603.18449 [cs.CR]   (or arXiv:2603.18449v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.18449 Focus to learn more Submission history From: Yue Zhao [view email] [v1] Thu, 19 Mar 2026 03:21:56 UTC (4,173 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)