RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models

• URL: http://arxiv.org/abs/2602.04448v1
• Date: Wed, 04 Feb 2026 11:19:15 GMT
• Title: RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
• Authors: Jiacheng Liang, Yuhui Wang, Tanqiu Jiang, Ting Wang,
• Abstract summary: We propose RASA, a routing-aware expert-level alignment framework.<n> RASA identifies experts disproportionately activated by successful jailbreaks, selectively fine-tunes only these experts under fixed routing.<n>Our results suggest that robust MoE safety alignment benefits from targeted expert repair rather than global parameter updates.
• Score: 10.741523413040559
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable degenerate optimization behaviors under standard full-parameter fine-tuning. In our preliminary experiments, we observe that naively applying full-parameter safety fine-tuning to MoE models can reduce attack success rates through routing or expert dominance effects, rather than by directly repairing Safety-Critical Experts. To address this challenge, we propose RASA, a routing-aware expert-level alignment framework that explicitly repairs Safety-Critical Experts while preventing routing-based bypasses. RASA identifies experts disproportionately activated by successful jailbreaks, selectively fine-tunes only these experts under fixed routing, and subsequently enforces routing consistency with safety-aligned contexts. Across two representative MoE architectures and a diverse set of jailbreak attacks, RASA achieves near-perfect robustness, strong cross-attack generalization, and substantially reduced over-refusal, while preserving general capabilities on benchmarks such as MMLU, GSM8K, and TruthfulQA. Our results suggest that robust MoE safety alignment benefits from targeted expert repair rather than global parameter updates, offering a practical and architecture-preserving alternative to prior approaches.

Related papers

• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment [43.86865924673546]
  We propose SafeThinker, an adaptive framework that allocates defensive resources via a lightweight gateway classifier.<n> Experiments show that SafeThinker significantly lowers attack success rates across diverse jailbreak strategies without compromising robustness.
  arXiv  Detail & Related papers  (2026-01-23T07:12:53Z)
• Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment [55.14890249389052]
  Existing defenses either embed safety recovery into fine-tuning or rely on fine-tuning-derived priors for post-hoc correction.<n>We propose textttQ-realign, a post-hoc defense method based on post-training quantization.<n>Our work provides a practical, turnkey solution for safety-aware deployment.
  arXiv  Detail & Related papers  (2026-01-13T00:07:24Z)
• Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers [12.47462301643593]
  Large language models (LLMs) with Mixture-of-Experts (MoE) architectures achieve impressive performance and efficiency by dynamically routing inputs to specializedworks, known as experts.<n>We propose BadSwitch, a novel backdoor framework that integrates task-coupled dynamic trigger optimization with a sensitivity-guided Top-S expert tracing mechanism.
  arXiv  Detail & Related papers  (2025-10-15T12:11:02Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs [83.11815479874447]
  We propose a novel jailbreak attack framework, inspired by cognitive decomposition and biases in human cognition.<n>We employ cognitive decomposition to reduce the complexity of malicious prompts and relevance bias to reorganize prompts.<n>We also introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm.
  arXiv  Detail & Related papers  (2025-05-03T05:28:11Z)
• Representation Bending for Large Language Model Safety [27.842146980762934]
  Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks pose significant challenges.<n>This paper introduces RepBend, a novel approach that fundamentally disrupts the representations underlying harmful behaviors in LLMs.<n>RepBend achieves state-of-the-art performance, outperforming prior methods such as Circuit Breaker, RMU, and NPO, with up to 95% reduction in attack success rates.
  arXiv  Detail & Related papers  (2025-04-02T09:47:01Z)
• How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities [62.474732677086855]
  Large language model (LLM) routing has emerged as a crucial strategy for balancing computational costs with performance.<n>We propose the DSC benchmark: Diverse, Simple, and Categorized, an evaluation framework that categorizes router performance across a broad spectrum of query types.
  arXiv  Detail & Related papers  (2025-03-20T19:52:30Z)
• STAIR: Improving Safety Alignment with Introspective Reasoning [44.780098674618614]
  We propose STAIR, a framework that integrates SafeTy Alignment with Itrospective Reasoning.<n>We show that STAIR effectively mitigates harmful outputs while better preserving helpfulness, compared to instinctive alignment strategies.<n>With test-time scaling, STAIR achieves a safety performance comparable to Claude-3.5 against popular jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-04T15:02:55Z)
• Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment [103.05005690990271]
  Mixture of insighTful Experts (MoTE) is a novel framework that combines reasoning chains and expert mixtures to improve self-alignments.<n>MoTE significantly improves model safety, jailbreak resistance, and over-refusal capabilities, achieving performance comparable to OpenAI's state-of-the-art o1 model.
  arXiv  Detail & Related papers  (2024-05-01T15:06:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.