mlsanityData to 14 Oct 2026

Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN

arXiv 2103.04513 ↗First posted 8 Mar 2021cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks (CNNs) have achieved beyond human-level accuracy in the image classification task and are widely deployed in real-world environments. However, CNNs show vulnerability to adversarial perturbations that are well-designed noises aiming to mislead the classification models. In order to defend against the adversarial perturbations, adversarially trained GAN (ATGAN) is proposed to improve the adversarial robustness generalization of the state-of-the-art CNNs trained by adversarial training. ATGAN incorporates adversarial training into standard GAN training procedure to remove obfuscated gradients which can lead to a false sense in defending against the adversarial perturbations and are commonly observed in existing GANs-based adversarial defense methods. Moreover, ATGAN adopts the image-to-image generator as data augmentation to increase the sample complexity needed for adversarial robustness generalization in adversarial training. Experimental results in MNIST SVHN and CIFAR-10 datasets show that the proposed method doesn't rely on obfuscated gradients and achieves better global adversarial robustness generalization performance than the adversarially trained state-of-the-art CNNs.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 52 of its 63 references that are in the map. First posted on arXiv 8 Mar 2021.

Builds on

52 of 63 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2016Densely Connected Convolutional Networkscited by 6,720
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  11. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  12. 2014Going Deeper with Convolutionscited by 4,241
38 more
  1. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2015Fast R-CNNcited by 2,933
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  11. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  12. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  13. 2017One pixel attack for fooling deep neural networkscited by 582
  14. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  15. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  16. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  17. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  18. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  19. 2018Adversarially Robust Generalization Requires More Datacited by 318
  20. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  21. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  22. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  23. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  24. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  25. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  26. 2019Are Labels Required for Improving Adversarial Robustness?cited by 163
  27. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  28. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
  29. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 153
  30. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  31. 2019Adversarially Robust Generalization Just Requires More Unlabeled Datacited by 76
  32. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  33. 2017Houdini: Fooling Deep Structured Prediction Modelscited by 50
  34. 2019Robustness to Adversarial Perturbations in Learning from Incomplete Datacited by 49
  35. 2017Defense against Universal Adversarial Perturbationscited by 48
  36. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  37. 2017DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samplescited by 22
  38. 2017Generative Adversarial Trainer: Defense to Adversarial Perturbations with GANcited by 20

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Your Out-of-Distribution Detection Method is Not Robust!cited by 16