# Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks

arXiv: https://arxiv.org/abs/2607.23015 · HTML: https://mlsanity.com/paper/2607.23015/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 25 Jul 2026.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 26 of 26)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [BlockPruner: Fine-grained Pruning for Large Language Models](https://mlsanity.com/paper/2406.10594/) (2024)
- [NeuroStrike: Neuron-Level Attacks on Aligned LLMs](https://mlsanity.com/paper/2509.11864/) (2025)
- [TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts](https://mlsanity.com/paper/2506.07596/) (2025)
- [SafeNeuron: Neuron-Level Safety Alignment for Large Language Models](https://mlsanity.com/paper/2602.12158/) (2026)
- [Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction](https://mlsanity.com/paper/2509.15202/) (2025)
- [NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models](https://mlsanity.com/paper/2504.21053/) (2025)
- [NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs](https://mlsanity.com/paper/2508.09473/) (2025)

## Abstract (arXiv)

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.