mlsanityData to 14 Oct 2026

Adversarial Robustness of Discriminative Self-Supervised Learning in Vision

arXiv 2503.06361 ↗First posted 8 Mar 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning (SSL) has advanced significantly in visual representation learning, yet comprehensive evaluations of its adversarial robustness remain limited. In this study, we evaluate the adversarial robustness of seven discriminative self-supervised models and one supervised model across diverse tasks, including ImageNet classification, transfer learning, segmentation, and detection. Our findings suggest that discriminative SSL models generally exhibit better robustness to adversarial attacks compared to their supervised counterpart on ImageNet, with this advantage extending to transfer learning when using linear evaluation. However, when fine-tuning is applied, the robustness gap between SSL and supervised models narrows considerably. Similarly, this robustness advantage diminishes in segmentation and detection tasks. We also investigate how various factors might influence adversarial robustness, including architectural choices, training duration, data augmentations, and batch sizes. Our analysis contributes to the ongoing exploration of adversarial robustness in visual self-supervised representation systems.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 56 of its 78 references that are in the map. First posted on arXiv 8 Mar 2025.

Builds on

56 of 78 references.

References · 56

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  11. 2013Intriguing properties of neural networkscited by 5,155
  12. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
38 more
  1. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  2. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  3. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  4. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  6. 2013Describing Textures in the Wildcited by 2,125
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  8. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  9. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  10. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  11. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 694
  12. 2019Self-labelling via simultaneous clustering and representation learningcited by 528
  13. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  14. 2018Adversarially Robust Generalization Requires More Datacited by 318
  15. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  16. 2023A Cookbook of Self-Supervised Learningcited by 250
  17. 2016What makes ImageNet good for transfer learning?cited by 192
  18. 2021Are Transformers More Robust Than CNNs?cited by 187
  19. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  20. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 153
  21. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  22. 2018Are adversarial examples inevitable?cited by 113
  23. 2020Contrastive Learning with Adversarial Examplescited by 91
  24. 2016Robustness of classifiers: from adversarial to random noisecited by 88
  25. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  26. 2023Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Taskscited by 72
  27. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  28. 2022T-SEA: Transfer-based Self-Ensemble Attack on Object Detectioncited by 59
  29. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  30. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  31. 2022Self-Supervised Learning with an Information Maximization Criterioncited by 38
  32. 2022An Impartial Take to the CNN vs Transformer Robustness Contestcited by 34
  33. 2020Universal Adversarial Perturbations: A Surveycited by 28
  34. 2022Proximal Splitting Adversarial Attacks for Semantic Segmentationcited by 23
  35. 2022Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustnesscited by 20
  36. 2023Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learningcited by 20
  37. 2022Is Self-Supervised Learning More Robust Than Supervised Learning?cited by 17
  38. 2023Adversarial Examples Are Not Real Featurescited by 16

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Margin-Drop Coordinates for Cross-Budget Robustness Evaluationcited by 0