mlsanityData to 7 Oct 2026

Sustainable Self-evolution Adversarial Training

arXiv 2412.02270 ↗First posted 3 Dec 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors.Code is available at https://github.com/aup520/SSEAT

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 77 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

45 of 77 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  9. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  10. 2016Adversarial Machine Learning at Scalecited by 934
  11. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  12. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
33 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  2. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  3. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  4. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  5. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  6. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  7. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  8. 2023Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Modelscited by 106
  9. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 95
  10. 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusioncited by 75
  11. 2023Online Prototype Learning for Online Continual Learningcited by 53
  12. 2022Exploring Example Influence in Continual Learningcited by 44
  13. 2015A Unified Gradient Regularization Family for Adversarial Examplescited by 43
  14. 2022Make Some Noise: Reliable and Efficient Single-Step Adversarial Trainingcited by 42
  15. 2023An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferabilitycited by 42
  16. 2023MP-Former: Mask-Piloted Transformer for Image Segmentationcited by 39
  17. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  18. 2023Reinforcement Learning-Based Black-Box Model Inversion Attackscited by 33
  19. 2021Delving into Data: Effectively Substitute Training for Black-box Attackcited by 27
  20. 2020SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothingcited by 26
  21. 2023CapDet: Unifying Dense Captioning and Open-World Detection Pretrainingcited by 26
  22. 2023Improving Generalization of Adversarial Training via Robust Critical Fine-Tuningcited by 23
  23. 2022Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularizationcited by 22
  24. 2023CGBA: Curvature-aware Geometric Black-box Attackcited by 20
  25. 2023Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regressioncited by 18
  26. 2022Enhanced Training of Query-Based Object Detection via Selective Query Recollectioncited by 17
  27. 2023SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Datacited by 17
  28. 2023The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attackscited by 15
  29. 2023Fast Adversarial Training with Smooth Convergencecited by 14
  30. 20233DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attackcited by 9
  31. 2022DST: Dynamic Substitute Training for Data-free Black-box Attackcited by 7
  32. 2023CLR: Channel-wise Lightweight Reprogramming for Continual Learningcited by 6
  33. 2023CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Roboticscited by 2

Built on by

Not cited yet.