mlsanityData to 7 Oct 2026

Analysis and Extensions of Adversarial Training for Video Classification

arXiv 2206.07953 ↗First posted 16 Jun 2022cs.CV cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as a defense for video classification has not been thoroughly studied. Our first contribution is to show that generating optimal attacks for video requires carefully tuning the attack parameters, especially the step size. Notably, we show that the optimal step size varies linearly with the attack budget. Our second contribution is to show that using a smaller (sub-optimal) attack budget at training time leads to a more robust performance at test time. Based on these findings, we propose three defenses against attacks with variable attack budgets. The first one, Adaptive AT, is a technique where the attack budget is drawn from a distribution that is adapted as training iterations proceed. The second, Curriculum AT, is a technique where the attack budget is increased as training iterations proceed. The third, Generative AT, further couples AT with a denoising generative adversarial network to boost robust performance. Experiments on the UCF101 dataset demonstrate that the proposed methods improve adversarial robustness against multiple attack types.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 38 of its 46 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

38 of 46 references.

References · 38

  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. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2016Adversarial Machine Learning at Scalecited by 934
  11. 2018Robustness May Be at Odds with Accuracycited by 873
  12. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
26 more
  1. 2016Pixel Recurrent Neural Networkscited by 814
  2. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  3. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  4. 2017Countering Adversarial Images using Input Transformationscited by 517
  5. 2020Overfitting in adversarially robust deep learningcited by 504
  6. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  7. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  8. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  9. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  10. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  11. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
  12. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  13. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  14. 2016Spatiotemporal Residual Networks for Video Action Recognitioncited by 91
  15. 2018Curriculum Adversarial Trainingcited by 89
  16. 2015Learning with a Strong Adversarycited by 68
  17. 2019Black-box Adversarial Attacks on Video Recognition Modelscited by 58
  18. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  19. 2018Sparse Adversarial Perturbations for Videoscited by 56
  20. 2020Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attackscited by 45
  21. 2020Over-the-Air Adversarial Flickering Attacks against Video Recognition Networkscited by 35
  22. 2020Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?cited by 31
  23. 2017Attacking the Madry Defense Model with L1-based Adversarial Examplescited by 21
  24. 2018Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networkscited by 21
  25. 2020Defending Against Multiple and Unforeseen Adversarial Videoscited by 19
  26. 2018Adversarial Attacks for Optical Flow-Based Action Recognition Classifierscited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 6; 2025: 2; 2026: 1.

11 papers.

  1. 2024R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Modelcited by 56
  2. 2025Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videoscited by 9
  3. 2024Adversarial Training: A Surveycited by 6
  4. 2024Can Implicit Bias Imply Adversarial Robustness?cited by 5
  5. 2024Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perceptioncited by 5
  6. 2025VideoPure: Diffusion-based Adversarial Purification for Video Recognitioncited by 5
  7. 2023Improve Video Representation with Temporal Adversarial Augmentationcited by 3
  8. 2026Exposing and Defending the Achilles' Heel of Video Mixture-of-Expertscited by 3
  9. 2022Adversarially Robust Video Perception by Seeing Motioncited by 2
  10. 2024Adaptive Batch Normalization Networks for Adversarial Robustnesscited by 1
  11. 2024Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweightercited by 0