mlsanityData to 7 Oct 2026

Adversarial Defense via Image Denoising with Chaotic Encryption

arXiv 2203.10290 ↗First posted 19 Mar 2022cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

In the literature on adversarial examples, white box and black box attacks have received the most attention. The adversary is assumed to have either full (white) or no (black) access to the defender's model. In this work, we focus on the equally practical gray box setting, assuming an attacker has partial information. We propose a novel defense that assumes everything but a private key will be made available to the attacker. Our framework uses an image denoising procedure coupled with encryption via a discretized Baker map. Extensive testing against adversarial images (e.g. FGSM, PGD) crafted using various gradients shows that our defense achieves significantly better results on CIFAR-10 and CIFAR-100 than the state-of-the-art gray box defenses in both natural and adversarial accuracy.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 19 Mar 2022.

Builds on

19 of 25 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  10. 2017Countering Adversarial Images using Input Transformationscited by 517
  11. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  12. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
7 more
  1. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  2. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
  3. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 70
  4. 2018On the Robustness of the CVPR 2018 White-Box Adversarial Example Defensescited by 40
  5. 2019Defending against adversarial attacks by randomized diversificationcited by 14
  6. 2019Convolutional Neural Networks on Randomized Datacited by 6
  7. 2018Secure Detection of Image Manipulation by means of Random Feature Selectioncited by 4

Built on by

Not cited yet.