Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM
cs.AI, cs.CR, cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- A Review of Sparse Expert Models in Deep Learning
- RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
- Mixtral of Experts
- Qwen3 Technical Report
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems