mlsanityData to 7 Oct 2026

A2: Efficient Automated Attacker for Boosting Adversarial Training

arXiv 2210.03543 ↗First posted 7 Oct 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Based on the significant improvement of model robustness by AT (Adversarial Training), various variants have been proposed to further boost the performance. Well-recognized methods have focused on different components of AT (e.g., designing loss functions and leveraging additional unlabeled data). It is generally accepted that stronger perturbations yield more robust models. However, how to generate stronger perturbations efficiently is still missed. In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training. A2 is a parameterized automated attacker to search in the attacker space for the best attacker against the defense model and examples. Extensive experiments across different datasets demonstrate that A2 generates stronger perturbations with low extra cost and reliably improves the robustness of various AT methods against different attacks.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

24 of 41 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  8. 2016Wide Residual Networkscited by 3,057
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  11. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  12. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
12 more
  1. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  2. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  3. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  4. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
  5. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  6. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  7. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  8. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  9. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  10. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  11. 2014A* Samplingcited by 150
  12. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 6; 2024: 2; 2025: 1.

10 papers.

  1. 2023DiffUTE: Universal Text Editing Diffusion Modelcited by 44
  2. 2023Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularizationcited by 42
  3. 2023Improving the Transferability of Adversarial Samples by Path-Augmented Methodcited by 36
  4. 2022Hierarchical Dynamic Image Harmonizationcited by 12
  5. 2024Adversarial Training: A Surveycited by 6
  6. 2023Backpropagation Path Search On Adversarial Transferabilitycited by 4
  7. 2024Edge Detectors Can Make Deep Convolutional Neural Networks More Robustcited by 2
  8. 2025TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularizationcited by 1
  9. 2023Beckman Defensecited by 0
  10. 2023Improving the Robustness of Deep Convolutional Neural Networks Through Feature Learningcited by 0