CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification
Not on the map. Why?
Abstract (arXiv)
Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation. Adversarial examples, which are carefully crafted with a malicious purpose, can lead to erroneous predictions, resulting in catastrophic accidents. To mitigate the effects of adversarial attacks, we propose a novel purification model called CAP-GAN. CAP-GAN takes account of the idea of pixel-level and feature-level consistency to achieve reasonable purification under cycle-consistent learning. Specifically, we utilize the guided attention module and knowledge distillation to convey meaningful information to the purification model. Once a model is fully trained, inputs would be projected into the purification model and transformed into clean-like images. We vary the capacity of the adversary to argue the robustness against various types of attack strategies. On the CIFAR-10 dataset, CAP-GAN outperforms other pre-processing based defenses under both black-box and white-box settings.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 31 references that are in the map. First posted on arXiv 15 Feb 2021.
Builds on
28 of 31 references.
References · 28
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
16 more
- 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
- 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
- 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
- 2016A study of the effect of JPG compression on adversarial imagescited by 196
- 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
- 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
- 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
- 2017Efficient Defenses Against Adversarial Attackscited by 53
- 2019One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examplescited by 8
Built on by
Citing papers per year: 2023: 1.
1 paper.