mlsanityData to 7 Oct 2026

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

arXiv 2202.11898 ↗First posted 24 Feb 2022cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 this feature at the channel level, i.e. the activation of a channel is uniformly scaled by a factor. In this paper, we investigate the intermediate activation manipulation at a more fine-grained level. Instead of uniformly scaling the activation, we individually adjust each element within an activation and thus propose Element-Wise Activation Scaling, dubbed EWAS, to improve CNNs' adversarial robustness. Experimental results on ResNet-18 and WideResNet with CIFAR10 and SVHN show that EWAS significantly improves the robustness accuracy. Especially for ResNet18 on CIFAR10, EWAS increases the adversarial accuracy by 37.65% to 82.35% against C&W attack. EWAS is simple yet very effective in terms of improving robustness. The codes are anonymously available at https://anonymous.4open.science/r/EWAS-DD64.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 24 Feb 2022.

Builds on

21 of 36 references.

References · 21

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  9. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  10. 2017One pixel attack for fooling deep neural networkscited by 579
  11. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  12. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
9 more
  1. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  2. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  3. 2018Adversarial Logit Pairingcited by 224
  4. 2019Adversarially Robust Distillationcited by 124
  5. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  6. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  7. 2019Model Compression with Adversarial Robustness: A Unified Optimization Frameworkcited by 71
  8. 2021CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selectioncited by 21
  9. 2019AdvGAN++ : Harnessing latent layers for adversary generationcited by 20

Built on by

Not cited yet.