Papers › Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network...
Robust Mode Connectivity-Oriented Adversarial Defense: Enhancing Neural Network Robustness Against Diversified ℓₚ Attacks
Ren Wang, YuXuan Li, Sijia Liu
Adversarial robustness is a key concept in measuring the ability of neural networks to defend against adversarial attacks during the inference phase. Recent studies have shown that despite the success of improving adversarial robustness against a single type of attack using robust training techniques, models are still vulnerable to diversified ℓₚ attacks. To achieve diversified ℓₚ robustness, we propose a novel robust mode connectivity (RMC)-oriented adversarial defense that contains two population-based learning phases. The first phase, RMC, is able to search the model parameter space between two pre-trained models and find a path containing points with high robustness against diversified ℓₚ attacks. In light of the effectiveness of RMC, we develop a second phase, RMC-based optimization, with RMC serving as the basic unit for further enhancement of neural network diversified ℓₚ robustness. To increase computational efficiency, we incorporate learning with a self-robust mode connectivity (SRMC) module that enables the fast proliferation of the population used for endpoints of RMC. Furthermore, we draw parallels between SRMC and the human immune system. Experimental results on various datasets and model architectures demonstrate that the proposed defense methods can achieve high diversified ℓₚ robustness against ℓ_∞, ℓ₂, ℓ₁, and hybrid attacks. Codes are available at \url{https://github.com/wangren09/MCGR}.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections