Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Jiacheng, Wang, Yuhui, Jiang, Tanqiu, Wang, Ting
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GraphRAG under Fire
by: Liang, Jiacheng, et al.
Published: (2025)

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models
by: Liang, Jiacheng, et al.
Published: (2025)

Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
by: Jiang, Yukun, et al.
Published: (2026)

MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
by: Wang, Yuhui, et al.
Published: (2026)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
by: Jiang, Tanqiu, et al.
Published: (2024)

Self-Destructive Language Model
by: Wang, Yuhui, et al.
Published: (2025)

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
by: Zhang, Yi, et al.
Published: (2025)

Your Agent Can Defend Itself against Backdoor Attacks
by: Changjiang, Li, et al.
Published: (2025)

PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning
by: Feng, Yu, et al.
Published: (2025)

MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
by: Jiang, Weisen, et al.
Published: (2026)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
by: Li, Yuxi, et al.
Published: (2024)

Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection
by: Shokouhinejad, Hossein, et al.
Published: (2026)

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
by: Huang, Tiansheng, et al.
Published: (2025)

Mixture of Robust Experts (MoRE):A Robust Denoising Method towards multiple perturbations
by: Cheng, Hao, et al.
Published: (2021)

Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
by: Liu, Guozhi, et al.
Published: (2025)

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
by: Jiang, Fengqing, et al.
Published: (2025)

MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
by: Cornacchia, Giandomenico, et al.
Published: (2024)

Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
by: Zaree, Pedram, et al.
Published: (2025)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
by: Ghosal, Soumya Suvra, et al.
Published: (2024)

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models
by: Fang, Junfeng, et al.
Published: (2025)

Investigating the Impact of Quantization on Adversarial Robustness
by: Li, Qun, et al.
Published: (2024)

Stealing User Prompts from Mixture of Experts
by: Yona, Itay, et al.
Published: (2024)

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
by: Lai, Zhenglin, et al.
Published: (2025)

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
by: Wang, Qingyue, et al.
Published: (2025)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
by: Li, Jianwei, et al.
Published: (2025)

Improved Algorithms for Differentially Private Language Model Alignment
by: Chen, Keyu, et al.
Published: (2025)

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
by: Yuan, Leitao, et al.
Published: (2026)

Understanding the Effects of Safety Unalignment on Large Language Models
by: Halloran, John T.
Published: (2026)

History-Aware and Dynamic Client Contribution in Federated Learning
by: Ghosh, Bishwamittra, et al.
Published: (2024)

Research on Dynamic Data Flow Anomaly Detection based on Machine Learning
by: Wang, Liyang, et al.
Published: (2024)

Differentially Private Preference Data Synthesis for Large Language Model Alignment
by: Gao, Fengyu, et al.
Published: (2026)

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
by: Jiang, Tanqiu, et al.
Published: (2025)

Hijack Vertical Federated Learning Models As One Party
by: Qiu, Pengyu, et al.
Published: (2022)

Structure-Aware Distributed Backdoor Attacks in Federated Learning
by: Jian, Wang, et al.
Published: (2026)

Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
by: Liu, Huikang, et al.
Published: (2026)

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models
by: Hossain, Ismail, et al.
Published: (2026)

Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
by: Wu, Jinman, et al.
Published: (2026)

UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models
by: Sun, Yuhao, et al.
Published: (2025)

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
by: Radosevich, Brandon, et al.
Published: (2025)