mlsanityData to 7 Oct 2026

AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense

arXiv 2107.06456 ↗First posted 14 Jul 2021cs.LG cs.AI cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose an AID-purifier that can boost the robustness of adversarially-trained networks by purifying their inputs. AID-purifier is an auxiliary network that works as an add-on to an already trained main classifier. To keep it computationally light, it is trained as a discriminator with a binary cross-entropy loss. To obtain additionally useful information from the adversarial examples, the architecture design is closely related to information maximization principles where two layers of the main classification network are piped to the auxiliary network. To assist the iterative optimization procedure of purification, the auxiliary network is trained with AVmixup. AID-purifier can be used together with other purifiers such as PixelDefend for an extra enhancement. The overall results indicate that the best performing adversarially-trained networks can be enhanced by the best performing purification networks, where AID-purifier is a competitive candidate that is light and robust.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 14 Jul 2021.

Builds on

35 of 48 references.

References · 35

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Wide Residual Networkscited by 3,057
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  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. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
23 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2018Deep Graph Infomaxcited by 1,101
  3. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  5. 2018MINE: Mutual Information Neural Estimationcited by 680
  6. 2013Network In Networkcited by 600
  7. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  8. 2017Countering Adversarial Images using Input Transformationscited by 517
  9. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  10. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  11. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  12. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  13. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  14. 2017On Detecting Adversarial Perturbationscited by 232
  15. 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
  16. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  17. 2019Understanding the Limitations of Variational Mutual Information Estimatorscited by 140
  18. 2020Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalizationcited by 73
  19. 2017Adversarial and Clean Data Are Not Twinscited by 52
  20. 2019Enhancing Adversarial Defense by k-Winners-Take-Allcited by 51
  21. 2021Online Adversarial Purification based on Self-Supervisioncited by 45
  22. 2017Learning Independent Features with Adversarial Nets for Non-linear ICAcited by 33
  23. 2018Learning Speaker Representations with Mutual Informationcited by 26

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 4; 2025: 2.

10 papers.

  1. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  2. 2025CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIPcited by 23
  3. 2024Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defencescited by 9
  4. 2023Robust Feature Inference: A Test-time Defense Strategy using Spectral Projectionscited by 3
  5. 2024Interpretability-Guided Test-Time Adversarial Defensecited by 3
  6. 2022Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responsescited by 1
  7. 2024Adversarial Examples are Misaligned in Diffusion Model Manifoldscited by 1
  8. 2024ZeroPur: Succinct Training-Free Adversarial Purificationcited by 1
  9. 2025Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defensecited by 1
  10. 2023DAD++: Improved Data-free Test Time Adversarial Defensecited by 0