mlsanityData to 7 Oct 2026

Adversarial Robust Memory-Based Continual Learner

arXiv 2311.17608 ↗First posted 29 Nov 2023cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Despite the remarkable advances that have been made in continual learning, the adversarial vulnerability of such methods has not been fully discussed. We delve into the adversarial robustness of memory-based continual learning algorithms and observe limited robustness improvement by directly applying adversarial training techniques. Preliminary studies reveal the twin challenges for building adversarial robust continual learners: accelerated forgetting in continual learning and gradient obfuscation in adversarial robustness. In this study, we put forward a novel adversarial robust memory-based continual learner that adjusts data logits to mitigate the forgetting of pasts caused by adversarial samples. Furthermore, we devise a gradient-based data selection mechanism to overcome the gradient obfuscation caused by limited stored data. The proposed approach can widely integrate with existing memory-based continual learning as well as adversarial training algorithms in a plug-and-play way. Extensive experiments on Split-CIFAR10/100 and Split-Tiny-ImageNet demonstrate the effectiveness of our approach, achieving up to 8.13% higher accuracy for adversarial data.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

44 of 63 references.

References · 44

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2016Learning without Forgettingcited by 2,465
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2016Progressive Neural Networkscited by 1,332
  8. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2021Learning to Prompt for Continual Learningcited by 938
  11. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  12. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
32 more
  1. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  2. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  3. 2019Gradient based sample selection for online continual learningcited by 568
  4. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  5. 2019On Tiny Episodic Memories in Continual Learningcited by 299
  6. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  7. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  8. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 215
  9. 2023Class-Incremental Learning: A Surveycited by 209
  10. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  11. 2020Bag of Tricks for Adversarial Trainingcited by 199
  12. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  13. 2018Towards Robust Evaluations of Continual Learningcited by 148
  14. 2019Scalable and Order-robust Continual Learning with Additive Parameter Decompositioncited by 125
  15. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  16. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
  17. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 94
  18. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  19. 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
  20. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  21. 2021Adversarial Robustness under Long-Tailed Distributioncited by 50
  22. 2021GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularizationcited by 34
  23. 2021Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connectorcited by 34
  24. 2021Detection and Continual Learning of Novel Face Presentation Attackscited by 33
  25. 2022Improving Task-free Continual Learning by Distributionally Robust Memory Evolutioncited by 29
  26. 2020Open-set Adversarial Defensecited by 27
  27. 2023Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learningcited by 27
  28. 2023Improving Generalization of Adversarial Training via Robust Critical Fine-Tuningcited by 23
  29. 2020Targeted Forgetting and False Memory Formation in Continual Learners through Adversarial Backdoor Attackscited by 14
  30. 2023BrainWash: A Poisoning Attack to Forget in Continual Learningcited by 9
  31. 2022Susceptibility of Continual Learning Against Adversarial Attackscited by 8
  32. 2022Queried Unlabeled Data Improves and Robustifies Class-Incremental Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2024Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspacecited by 14
  2. 2024Improving Data-aware and Parameter-aware Robustness for Continual Learningcited by 2
  3. 2025On Understanding of the Dynamics of Model Capacity in Continual Learningcited by 1
  4. 2026Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnosticscited by 0
  5. 2026Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recoverycited by 0