Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity
cs.LG
Submitted: 2026-08-26
Updated: 2026-08-26
Terminology
Sources
- Intriguing properties of neural networks
- Explaining and Harnessing Adversarial Examples
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
- Bridging Models to Defend: A Population-Based Strategy for Robust Adversarial Defense
- Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness
- Wide Residual Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks