Lune

AAAI2020顶会

Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks

Sekitoshi Kanai, Yasutoshi Ida, Yasuhiro Fujiwara, Masanori Yamada, Shuichi Adachi

摘要

We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convolution operations in CNNs commonly have structural sensitivity to specific noise composed of Fourier basis functions. By exploiting this sensitivity, they proposed a simple black-box adversarial attack: Single Fourier attack. To reduce structural sensitivity, we can use regularization of convolution filter weights since the sensitivity of linear transform can be assessed by the norm of the weights. However, standard regularization methods can prevent minimization of the loss function because they impose a tight constraint for obtaining high robustness. To solve this problem, Absum imposes a loose constraint; it penalizes the absolute values of the summation of the parameters in the convolution layers. Absum can improve robustness against single Fourier attack while being as simple and efficient as standard regularization methods (e.g., weight decay and L1 regularization). Our experiments demonstrate that Absum improves robustness against single Fourier attack more than standard regularization methods. Furthermore, we reveal that robust CNNs with Absum are more robust against transferred attacks due to decreasing the common sensitivity and against high-frequency noise than standard regularization methods. We also reveal that Absum can improve robustness against gradient-based attacks (projected gradient descent) when used with adversarial training.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 1 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper1

  1. Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?Wendong Zheng, Junyang Chen, Husheng Guo, Wenjian WangICML 2025

它引用的 Paper2

  1. Distillation as a Defense to Adversarial Perturbations Against Deep Neural NetworksNicolas Papernot, Patrick D. McDaniel, Xi Wu, Somesh Jha 等S&P 2016 · 3,275 次引用
  2. High-Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksHaohan Wang, Xindi Wu, Zeyi Huang, Eric P. XingCVPR 2020

相关 Paper

  1. Convolutional Normalization: Improving Deep Convolutional Network Robustness and TrainingSheng Liu, Xiao Li, Yuexiang Zhai, Chong You 等NeurIPS 2021 · 30 次引用
  2. Large Norms of CNN Layers Do Not Hurt Adversarial RobustnessYouwei Liang, Dong HuangAAAI 2021 · 13 次引用
  3. Improving Transferability of Adversarial Patches on Face Recognition With Generative ModelsZihao Xiao, Xianfeng Gao, Chilin Fu, Yinpeng Dong 等CVPR 2021
  4. LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency RegionsYaguan Qian, Shuke He, Chenyu Zhao, Jiaqiang Sha 等ICCV 2023 · 26 次引用
  5. Not All Low-Pass Filters are Robust in Graph Convolutional NetworksHeng Chang, Yu Rong, Tingyang Xu, Yatao Bian 等NeurIPS 2021 · 65 次引用
黄昏的海面,两侧是细线勾勒的悬崖