谁负责安全转移？识别和定位跨语言共享安全神经元
Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
AI总结：
本文提出通过识别和定位跨语言共享安全神经元，提升非高资源语言的安全性，采用神经元导向的训练策略增强模型跨语言防御一致性。
摘要：
多语言安全性仍然存在显著不平衡，导致非高资源（NHR）语言相比稳健的高资源（HR）语言更加脆弱。此外，尽管观察到跨语言表示转移，驱动安全对齐的神经机制仍不清楚。在本文中，我们发现LLMs包含一组跨语言共享安全神经元（SS-Neurons），这是一个 remarkably 小但至关重要的神经子集，共同调节跨语言的安全行为。我们首先识别了单语言安全神经元（MS-Neurons）并通过针对性激活和抑制验证了其在安全拒绝行为中的因果作用。我们的跨语言分析随后发现SS-Neurons是HR和NHR语言之间共享的MS-Neurons子集，充当从HR到NHR领域转移安全能力的桥梁。我们观察到抑制这些神经元会导致NHR语言中的同时安全下降，而强化它们则提高了跨语言防御的一致性。基于这些见解，我们提出了一种基于神经元的简单训练策略，根据语言资源分布和模型架构针对SS-Neurons进行训练。实验表明，对这个微小神经子集进行微调优于最先进的方法，显著增强了NHR的安全性，同时保持了模型的通用能力。代码和数据集将在https://github.com/1518630367/SS-Neuron-Expansion提供。
英文摘要：
Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed cross-lingual representation transfer. In this paper, we find that LLMs contain a set of cross-lingual shared safety neurons (SS-Neurons), a remarkably small yet critical neuronal subset that jointly regulates safety behavior across languages. We first identify monolingual safety neurons (MS-Neurons) and validate their causal role in safety refusal behavior through targeted activation and suppression. Our cross-lingual analyses then identify SS-Neurons as the subset of MS-Neurons shared between HR and NHR languages, serving as a bridge to transfer safety capabilities from HR to NHR domains. We observe that suppressing these neurons causes concurrent safety drops across NHR languages, whereas reinforcing them improves cross-lingual defensive consistency. Building on these insights, we propose a simple neuron-oriented training strategy that targets SS-Neurons based on language resource distribution and model architecture. Experiments demonstrate that fine-tuning this tiny neuronal subset outperforms state-of-the-art methods, significantly enhancing NHR safety while maintaining the model's general capabilities. The code and dataset will be available athttps://github.com/1518630367/SS-Neuron-Expansion.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
