Large language models (LLMs) are safety-aligned before deployment to reduce harmful content generation. Yet neuron-level pruning attacks show that refusal can depend on a small set of removable units: disabling them can remove safety behavior while leaving much of the model usable. To address this problem, we introduce Mask2Shield (M2S), a masked-forward alignment method that trains a model under this functional pruning. The masked student must recover a safe refusal through the remaining computation, while a frozen, unmasked teacher supplies complete benign answers to limit capability drift. Across ten model configurations, M2S reduces successful recomputed pruning attacks from 80--279 to 1--44 out of 313 prompts while generally preserving four capability benchmarks. We also evaluate M2S with TwinBreak, which uses a different neuron-selection rule and iterative pruning procedure. Together, these results show that M2S makes targeted pruning less effective by reducing reliance on a small, removable safety-neuron set.

翻译：暂无翻译