mlsanityData to 7 Oct 2026

Enhanced countering adversarial attacks via input denoising and feature restoring

arXiv 2111.10075 ↗First posted 19 Nov 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite the fact that deep neural networks (DNNs) have achieved prominent performance in various applications, it is well known that DNNs are vulnerable to adversarial examples/samples (AEs) with imperceptible perturbations in clean/original samples. To overcome the weakness of the existing defense methods against adversarial attacks, which damages the information on the original samples, leading to the decrease of the target classifier accuracy, this paper presents an enhanced countering adversarial attack method IDFR (via Input Denoising and Feature Restoring). The proposed IDFR is made up of an enhanced input denoiser (ID) and a hidden lossy feature restorer (FR) based on the convex hull optimization. Extensive experiments conducted on benchmark datasets show that the proposed IDFR outperforms the various state-of-the-art defense methods, and is highly effective for protecting target models against various adversarial black-box or white-box attacks. footnoteSouce code is released at: hrefhttps://github.com/ID-FR/IDFRhttps://github.com/ID-FR/IDFR

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 19 Nov 2021.

Builds on

43 of 56 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2021Convex optimizationcited by 2,479
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2016Concrete Problems in AI Safetycited by 1,582
  12. 2016Practical Black-Box Attacks against Machine Learningcited by 893
31 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. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  5. 2019Adversarial Training for Free!cited by 638
  6. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  7. 2017Countering Adversarial Images using Input Transformationscited by 517
  8. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  9. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  10. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  11. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  12. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  13. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  14. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  15. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  16. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  17. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  18. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  19. 2021Adversarial purification with Score-based generative modelscited by 132
  20. 2018Are adversarial examples inevitable?cited by 113
  21. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 104
  22. 2019Metric Learning for Adversarial Robustnesscited by 77
  23. 2020Consistency Regularization for Certified Robustness of Smoothed Classifierscited by 73
  24. 2018Adversarial Examples: Opportunities and Challengescited by 62
  25. 2017Adversarial examples for generative modelscited by 58
  26. 2020Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspectivecited by 58
  27. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 56
  28. 2019Efficient Adversarial Training with Transferable Adversarial Examplescited by 54
  29. 2021Online Adversarial Purification based on Self-Supervisioncited by 45
  30. 2020Attribute-Guided Adversarial Training for Robustness to Natural Perturbationscited by 23
  31. 2021Stabilized Medical Image Attackscited by 10

Built on by

Not cited yet.