·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
FRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis10h◆Evaluating the Hidden Costs of Personalization in Large Language Models10h◆Stratified Consistency Distillation for Natural Language Formalization10h◆Adversarial Trust Poisoning in Vehicular Collaborative Perception10h◆VibeJam: A User Study Platform for Web Development with Agents10h◆Investigating Social Bias Changes in Quantized Language Models10h◆How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction10h◆CoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation10h◆EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents10h◆T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler10h◆Autoencoders in Function Space10h◆Propensity Straight-Through Gradients for Discrete Stochastic Systems10h◆GFlowNets and variational inference10h◆CogEvol: Towards Efficient and Reliable Learning Environment Generation10h◆XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals10h◆LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems10h◆Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation10h◆The Unsampled Truth: Quantifying Prompt Artifacts in LM Psychometrics10h◆A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction10h◆Evaluating Multilingual Sentence Embeddings for Translation Error Detection:An English--Greek Contrastive Study10h◆FRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis10h◆Evaluating the Hidden Costs of Personalization in Large Language Models10h◆Stratified Consistency Distillation for Natural Language Formalization10h◆Adversarial Trust Poisoning in Vehicular Collaborative Perception10h◆VibeJam: A User Study Platform for Web Development with Agents10h◆Investigating Social Bias Changes in Quantized Language Models10h◆How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction10h◆CoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation10h◆EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents10h◆T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler10h◆Autoencoders in Function Space10h◆Propensity Straight-Through Gradients for Discrete Stochastic Systems10h◆GFlowNets and variational inference10h◆CogEvol: Towards Efficient and Reliable Learning Environment Generation10h◆XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals10h◆LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems10h◆Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation10h◆The Unsampled Truth: Quantifying Prompt Artifacts in LM Psychometrics10h◆A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction10h◆Evaluating Multilingual Sentence Embeddings for Translation Error Detection:An English--Greek Contrastive Study10h◆
News/RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
arxiv
PublishedMay 7, 2026 at 4:00 AM
—neutral

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.02946v1 Announce Type: cross Abstract: Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly adopted to scale model capacity, understanding their safety robustness becomes essential. Existing

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivFRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis10harxivEvaluating the Hidden Costs of Personalization in Large Language Models10harxivStratified Consistency Distillation for Natural Language Formalization10harxivAdversarial Trust Poisoning in Vehicular Collaborative Perception10h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews