mlsanityData to 7 Oct 2026

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training

arXiv 2312.07067 ↗First posted 12 Dec 2023cs.LG cs.CR cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Adversarial training is often formulated as a min-max problem, however, concentrating only on the worst adversarial examples causes alternating repetitive confusion of the model, i.e., previously defended or correctly classified samples are not defensible or accurately classifiable in subsequent adversarial training. We characterize such non-ignorable samples as "hiders", which reveal the hidden high-risk regions within the secure area obtained through adversarial training and prevent the model from finding the real worst cases. We demand the model to prevent hiders when defending against adversarial examples for improving accuracy and robustness simultaneously. By rethinking and redefining the min-max optimization problem for adversarial training, we propose a generalized adversarial training algorithm called Hider-Focused Adversarial Training (HFAT). HFAT introduces the iterative evolution optimization strategy to simplify the optimization problem and employs an auxiliary model to reveal hiders, effectively combining the optimization directions of standard adversarial training and prevention hiders. Furthermore, we introduce an adaptive weighting mechanism that facilitates the model in adaptively adjusting its focus between adversarial examples and hiders during different training periods. We demonstrate the effectiveness of our method based on extensive experiments, and ensure that HFAT can provide higher robustness and accuracy.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 12 Dec 2023.

Builds on

28 of 37 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2016Wide Residual Networkscited by 3,057
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  11. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  12. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
16 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  2. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  3. 2020Overfitting in adversarially robust deep learningcited by 504
  4. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  5. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  6. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  7. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  8. 2019Adversarial Training Can Hurt Generalizationcited by 131
  9. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  10. 2020Adversarial Distributional Training for Robust Deep Learningcited by 79
  11. 2020On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Themcited by 59
  12. 2022Make Some Noise: Reliable and Efficient Single-Step Adversarial Trainingcited by 42
  13. 2023Randomized Adversarial Training via Taylor Expansioncited by 28
  14. 2017Residual Convolutional CTC Networks for Automatic Speech Recognitioncited by 21
  15. 2022Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognitioncited by 11
  16. 2022Adversarial Coreset Selection for Efficient Robust Trainingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2026GENSR: Symbolic Regression Based in Equation Generative Spacecited by 6
  2. 2024Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-offcited by 5
  3. 2024DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Modelscited by 3
  4. 2025Weakly Supervised Contrastive Adversarial Training for Learning Robust Features from Semi-supervised Datacited by 1
  5. 2026Inevitable Encounters: Backdoor Attacks Involving Lossy Compressioncited by 0