mlsanityData to 7 Oct 2026

An Eye for an Eye: Defending against Gradient-based Attacks with Gradients

arXiv 2202.01117 ↗First posted 2 Feb 2022cs.CV cs.CR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Deep learning models have been shown to be vulnerable to adversarial attacks. In particular, gradient-based attacks have demonstrated high success rates recently. The gradient measures how each image pixel affects the model output, which contains critical information for generating malicious perturbations. In this paper, we show that the gradients can also be exploited as a powerful weapon to defend against adversarial attacks. By using both gradient maps and adversarial images as inputs, we propose a Two-stream Restoration Network (TRN) to restore the adversarial images. To optimally restore the perturbed images with two streams of inputs, a Gradient Map Estimation Mechanism is proposed to estimate the gradients of adversarial images, and a Fusion Block is designed in TRN to explore and fuse the information in two streams. Once trained, our TRN can defend against a wide range of attack methods without significantly degrading the performance of benign inputs. Also, our method is generalizable, scalable, and hard to bypass. Experimental results on CIFAR10, SVHN, and Fashion MNIST demonstrate that our method outperforms state-of-the-art defense methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 39 of its 45 references that are in the map. First posted on arXiv 2 Feb 2022.

Builds on

39 of 45 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  8. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  12. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
27 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  2. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  3. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  4. 2017Countering Adversarial Images using Input Transformationscited by 517
  5. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  6. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  7. 2019On Evaluating Adversarial Robustnesscited by 442
  8. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  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. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  12. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  13. 2018Adversarial Logit Pairingcited by 224
  14. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  15. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  16. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  17. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  18. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  19. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
  20. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 104
  21. 2018Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Networkcited by 68
  22. 2019Image Super-Resolution as a Defense Against Adversarial Attackscited by 64
  23. 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
  24. 2019Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attackscited by 54
  25. 2018Deep Defense: Training DNNs with Improved Adversarial Robustnesscited by 41
  26. 2019What it Thinks is Important is Important: Robustness Transfers through Input Gradientscited by 34
  27. 2020Ensemble Generative Cleaning with Feedback Loops for Defending Adversarial Attackscited by 9

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1.

2 papers.

  1. 2022UniCR: Universally Approximated Certified Robustness via Randomized Smoothingcited by 10
  2. 2023Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidencecited by 5