mlsanityData to 7 Oct 2026

The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training

arXiv 2211.00525 ↗First posted 1 Nov 2022cs.CV cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Although current deep learning techniques have yielded superior performance on various computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial training and its variants have been shown to be the most effective approaches to defend against adversarial examples. These methods usually regularize the difference between output probabilities for an adversarial and its corresponding natural example. However, it may have a negative impact if the model misclassifies a natural example. To circumvent this issue, we propose a novel adversarial training scheme that encourages the model to produce similar outputs for an adversarial example and its ``inverse adversarial'' counterpart. These samples are generated to maximize the likelihood in the neighborhood of natural examples. Extensive experiments on various vision datasets and architectures demonstrate that our training method achieves state-of-the-art robustness as well as natural accuracy. Furthermore, using a universal version of inverse adversarial examples, we improve the performance of single-step adversarial training techniques at a low computational cost.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 46 of its 59 references that are in the map. First posted on arXiv 1 Nov 2022.

Builds on

46 of 59 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  9. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  10. 2016Wide Residual Networkscited by 3,057
  11. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
34 more
  1. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  2. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  3. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  5. 2019Natural Adversarial Examplescited by 1,401
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  8. 2016Universal adversarial perturbationscited by 774
  9. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  10. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  11. 2019Adversarial Training for Free!cited by 638
  12. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  13. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  14. 2018Object Detection with Deep Learning: A Reviewcited by 524
  15. 2020Overfitting in adversarially robust deep learningcited by 504
  16. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  17. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  18. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  19. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  20. 2020Understanding and Improving Fast Adversarial Trainingcited by 213
  21. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  22. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  23. 2021Adversarial purification with Score-based generative modelscited by 132
  24. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  25. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  26. 2018Universal Adversarial Trainingcited by 85
  27. 2019Metric Learning for Adversarial Robustnesscited by 77
  28. 2020Understanding Catastrophic Overfitting in Single-step Adversarial Trainingcited by 75
  29. 2021Probabilistic Margins for Instance Reweighting in Adversarial Trainingcited by 57
  30. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  31. 2021Exploring Memorization in Adversarial Trainingcited by 55
  32. 2020Unadversarial Examples: Designing Objects for Robust Visioncited by 45
  33. 2022Make Some Noise: Reliable and Efficient Single-Step Adversarial Trainingcited by 42
  34. 2016Early Methods for Detecting Adversarial Imagescited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 8; 2026: 3.

22 papers.

Sort:

By area:

  1. 2024MirrorCheck: Efficient Adversarial Defense for Vision-Language Modelscited by 19
  2. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
  3. 2025Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videoscited by 9
  4. 2025AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimizationcited by 8
  5. 2024Adversarial Training: A Surveycited by 6
  6. 2024Towards Adversarial Robustness via Debiased High-Confidence Logit Alignmentcited by 5
  7. 2023Splitting the Difference on Adversarial Trainingcited by 4
  8. 2023NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networkscited by 3
  9. 2026CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoningcited by 3
  10. 2024New Paradigm of Adversarial Training: Releasing Accuracy-Robustness Trade-Off via Dummy Classcited by 2
  11. 2024Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Trainingcited by 2
  12. 2025Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreakingcited by 2
10 more
  1. 2023Language Guided Adversarial Purificationcited by 1
  2. 2024Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shiftscited by 1
  3. 2025Your Classifier Can Do More: Towards Balancing the Gaps in Classification, Robustness, and Generationcited by 1
  4. 2025Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defensecited by 1
  5. 2025Parameter Interpolation Adversarial Training for Robust Image Classificationcited by 1
  6. 2026Hierarchically Robust Zero-shot Vision-language Modelscited by 1
  7. 2024Towards Trustworthy Unsupervised Domain Adaptation: A Representation Learning Perspective for Enhancing Robustness, Discrimination, and Generalizationcited by 0
  8. 2025Learning from Few Samples: A Novel Approach for High-Quality Malcode Generationcited by 0
  9. 2025NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbationscited by 0
  10. 2026Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learningcited by 0