Exploring Diversified Adversarial Robustness in Neural Networks via Robust Mode Connectivity
Abstract
This paper proposes a new method called robust mode connectivity (RMC) to enhance the adversarial robustness of neural networks (NNs) by exploring a wider range of parameter space. While adversarial training methods have shown promising results in enhancing the robustness of NNs against perturbations, they are limited by considering only a single type of perturbation during training and having limited search capability. RMC aims to address this limitation by considering multiple ℓp norm perturbations (p = 1, 2, ∞) and building on the concept of mode connectivity to identify a path of NNs with high robustness against different types of perturbations. The proposed method employs a multi steepest descent (MSD) algorithm to explore the parameter space and achieve diversified adversarial robustness. Experimental results on various datasets and architectures demonstrate the effectiveness of RMC.
Cite
Text
Wang et al. "Exploring Diversified Adversarial Robustness in Neural Networks via Robust Mode Connectivity." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00231Markdown
[Wang et al. "Exploring Diversified Adversarial Robustness in Neural Networks via Robust Mode Connectivity." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/wang2023cvprw-exploring/) doi:10.1109/CVPRW59228.2023.00231BibTeX
@inproceedings{wang2023cvprw-exploring,
title = {{Exploring Diversified Adversarial Robustness in Neural Networks via Robust Mode Connectivity}},
author = {Wang, Ren and Li, Yuxuan and Liu, Sijia},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2023},
pages = {2346-2352},
doi = {10.1109/CVPRW59228.2023.00231},
url = {https://mlanthology.org/cvprw/2023/wang2023cvprw-exploring/}
}