arXiv Machine Learning August 27, 2026 By Xu Zhang, Ren Wang

Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity

Read the original on arXiv Machine Learning →

Robust CurveMoE is a mixture‑of‑experts framework that protects neural networks against perturbations defined by multiple norm constraints. It connects norm‑specialized models through a low‑loss path, selectively expertises only influential layers, and shares the rest of the parameters across routing paths. The method introduces contribution‑guided partial updating to reduce curve‑construction cost and provides a theoretical bound on the objective gap between partial and full optimization, achieving consistent improvements in clean, norm‑specific, and Union accuracy on CIFAR‑100 and ImageNet‑100.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Aug 26

Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity

Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives with...

llms computer-vision safety

arXiv Machine Learning

3d ago

SAM-on-the-Curve: Sharpness-Aware Mode Connectivity for Robust Weight-Space Interpolation

arXiv:2609.17748v1 Announce Type: new Abstract: Deep neural networks that are independently trained to similar performance can be connected by low-loss parametric curves in weight space, a phenomenon...

By Alejandro Calatrava, Xu Zhang, Ren Wang

arXiv AI

Jul 1

Improving Certified Robustness via Adversarial Distillation

arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.

By Matteo Melis, Jesus Martinez Del Rincon, Vishal Sharma

efficiency benchmarks safety

arXiv AI

Jul 8

RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations

arXiv:2607. 06109v1 Announce Type: cross Abstract: Multi-perturbation adversarial training (MAT) aims to achieve robustness against multiple $\ell_p$ perturbations but suffers from robustness trade-offs between different threats.

By Woo Jae Kim, Kyle Min, Suhyeon Ha, Joonsung Jeon, Sung-eui Yoon

benchmarks safety

arXiv Machine Learning

Jul 7

Binary Iterative Method for Non-targeted Adversarial Attack

arXiv:2607. 04145v1 Announce Type: new Abstract: Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models.

By Naman Goyal, Milan Chaudhari

safety

arXiv Machine Learning

Jul 10

LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks

arXiv:2607. 07745v1 Announce Type: new Abstract: While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneously remains a central challenge.

By Arthur Chiron (IRIT, EPE UT), Franck Mamalet (IRIT, DTIPG - SNCF, UT3), Thomas Massena (IRIT, DTIPG - SNCF, UT3), Thomas Deltort (IRIT), Mathieu Serrurier (IRIT, UT2J)

benchmarks

One email a morning, machine-written

Related stories

Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity

SAM-on-the-Curve: Sharpness-Aware Mode Connectivity for Robust Weight-Space Interpolation

Improving Certified Robustness via Adversarial Distillation

RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations

Binary Iterative Method for Non-targeted Adversarial Attack

LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks