SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
This addresses the vulnerability of safety alignment in LLMs for developers and users, offering a more robust and interpretable method, though it is incremental as it builds on existing preference optimization techniques.
The paper tackles the problem of brittle safety alignment in large language models by proposing SafeNeuron, a neuron-level framework that redistributes safety representations to improve robustness, resulting in significant enhancements against neuron pruning attacks and reduced risks of misuse while preserving general capabilities.
Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making alignment brittle and easily bypassed through neuron-level attacks. Moreover, most existing alignment methods operate at the behavioral level, offering limited control over the model's internal safety mechanisms. In this work, we propose SafeNeuron, a neuron-level safety alignment framework that improves robustness by redistributing safety representations across the network. SafeNeuron first identifies safety-related neurons, then freezes these neurons during preference optimization to prevent reliance on sparse safety pathways and force the model to construct redundant safety representations. Extensive experiments across models and modalities demonstrate that SafeNeuron significantly improves robustness against neuron pruning attacks, reduces the risk of open-source models being repurposed as red-team generators, and preserves general capabilities. Furthermore, our layer-wise analysis reveals that safety behaviors are governed by stable and shared internal representations. Overall, SafeNeuron provides an interpretable and robust perspective for model alignment.