mlsanityData to 7 Oct 2026

Masking and Mixing Adversarial Training

arXiv 2302.08066 ↗First posted 16 Feb 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

While convolutional neural networks (CNNs) have achieved excellent performances in various computer vision tasks, they often misclassify with malicious samples, a.k.a. adversarial examples. Adversarial training is a popular and straightforward technique to defend against the threat of adversarial examples. Unfortunately, CNNs must sacrifice the accuracy of standard samples to improve robustness against adversarial examples when adversarial training is used. In this work, we propose Masking and Mixing Adversarial Training (M2AT) to mitigate the trade-off between accuracy and robustness. We focus on creating diverse adversarial examples during training. Specifically, our approach consists of two processes: 1) masking a perturbation with a binary mask and 2) mixing two partially perturbed images. Experimental results on CIFAR-10 dataset demonstrate that our method achieves better robustness against several adversarial attacks than previous methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 31 references that are in the map. First posted on arXiv 16 Feb 2023.

Builds on

31 of 31 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2016Wide Residual Networkscited by 3,057
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
19 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2018Robustness May Be at Odds with Accuracycited by 873
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2016Universal adversarial perturbationscited by 774
  5. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  6. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  7. 2019Adversarial Training for Free!cited by 638
  8. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  9. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  10. 2018Adversarially Robust Generalization Requires More Datacited by 318
  11. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  12. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  13. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  14. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  15. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  16. 2020Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalizationcited by 73
  17. 2020ResizeMix: Mixing Data with Preserved Object Information and True Labelscited by 68
  18. 2018Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attackscited by 48
  19. 2020Adversarial Patch Attacks on Monocular Depth Estimation Networkscited by 29

Built on by

Not cited yet.