Author

Wencheng Yang

h-index 0 View on Semantic Scholar

We have 1 of 1 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks

Mask2Shield (M2S), a masked-forward alignment method that trains a model under this functional pruning procedure, reduces successful recomputed pruning attacks from 80--279 to 1--44 out of 313 prompts while generally preserving four capability benchmarks.

Jincheng Ying, Ming-Hui Xu, Yinhao Xiao et al. · arXiv.org · 0 citations