mlsanityData to 14 Oct 2026

A3T: Accuracy Aware Adversarial Training

arXiv 2211.16316 ↗First posted 29 Nov 2022cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this paper, we identify one cause of overfitting related to current practices of generating adversarial samples from misclassified samples. To address this, we propose an alternative approach that leverages the misclassified samples to mitigate the overfitting problem. We show that our approach achieves better generalization while having comparable robustness to state-of-the-art adversarial training methods on a wide range of computer vision, natural language processing, and tabular tasks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

32 of 42 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  8. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  9. 2016Adversarial examples in the physical worldcited by 1,769
  10. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  11. 2016Adversarial Machine Learning at Scalecited by 936
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
20 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  2. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  3. 2020Overfitting in adversarially robust deep learningcited by 506
  4. 2020Large-Scale Adversarial Training for Vision-and-Language Representation Learningcited by 327
  5. 2018Adversarially Robust Generalization Requires More Datacited by 318
  6. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
  7. 2020Bag of Tricks for Adversarial Trainingcited by 200
  8. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 172
  9. 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
  10. 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
  11. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 85
  12. 2015Distributional Smoothing with Virtual Adversarial Trainingcited by 61
  13. 2020CAT: Customized Adversarial Training for Improved Robustnesscited by 61
  14. 2019Instance adaptive adversarial training: Improved accuracy tradeoffs in neural netscited by 55
  15. 2021Exploring Memorization in Adversarial Trainingcited by 55
  16. 2022Understanding Robust Overfitting of Adversarial Training and Beyondcited by 51
  17. 2018Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attackscited by 48
  18. 2018Evaluating and Understanding the Robustness of Adversarial Logit Pairingcited by 34
  19. 2022Impact of Adversarial Training on Robustness and Generalizability of Language Modelscited by 9
  20. 2022Alleviating Robust Overfitting of Adversarial Training With Consistency Regularizationcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3.

4 papers.

  1. 2024Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledgecited by 5
  2. 2024Explaining the role of Intrinsic Dimensionality in Adversarial Trainingcited by 2
  3. 2024SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledgecited by 1
  4. 2023Enhancing Accuracy and Robustness through Adversarial Training in Class Incremental Continual Learningcited by 0