paper-with-me

홈 › Papers

Improving Adversarial Robustness via Channel-wise Activation Suppressing

2021-03-11 · ICLR 2021 1 · Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Xingjun Ma, Yisen Wang

The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing works, in this paper, we highlight two new characteristics of adversarial examples from the channel-wise activation perspective: 1) the activation magnitudes of adversarial examples are higher than that of natural examples; and 2) the channels are activated more uniformly by adversarial examples than natural examples. We find that the state-of-the-art defense adversarial training has addressed the first issue of high activation magnitudes via training on adversarial examples, while the second issue of uniform activation remains. This motivates us to suppress redundant activation from being activated by adversarial perturbations via a Channel-wise Activation Suppressing (CAS) strategy. We show that CAS can train a model that inherently suppresses adversarial activation, and can be easily applied to existing defense methods to further improve their robustness. Our work provides a simple but generic training strategy for robustifying the intermediate layer activation of DNNs.

📄 PDF Abstract BibTeX arXiv:2103.08307

Code (1)

bymavis/CAS_ICLR2021 공식 구현 pytorch

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

2021-02-10 · Hanshu Yan, Jingfeng Zhang, Gang Niu, Jiashi Feng 외

We investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe …

Adversarial Robustnessfeature selection

Improving Robustness of Convolutional Neural Networks Using Element-Wise Activation Scaling

2022-02-24 · Zhi-Yuan Zhang, Di Liu

Recent works reveal that re-calibrating the intermediate activation of adversarial examples can improve the adversarial robustness of a CNN model. The state of the arts [Baiet al., 2021] and [Yanet al., 2021] explores th…

Adversarial Robustness

Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations

2022-02-26 · Metehan Cekic, Can Bakiskan, Upamanyu Madhow

While end-to-end training of Deep Neural Networks (DNNs) yields state of the art performance in an increasing array of applications, it does not provide insight into, or control over, the features being extracted. We rep…

image-classificationImage Classification

Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

2026-05-20 · Qishi Zhan, Ziheng Chen, Minxuan Hu arxiv

One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-prun…

Pixab-CAM: Attend Pixel, not Channel

2021-09-29 · Jaeeun Jang, Seokjun Kim, Hyeoncheol Kim

To understand the internal behaviors of convolution neural networks (CNNs), many class activation mapping (CAM) based methods, which generate an explanation map by a linear combination of channels and corresponding weigh…

Adversarial Attack