mlsanityData to 14 Oct 2026

Leveraging Generalizability of Image-to-Image Translation for Enhanced Adversarial Defense

arXiv 2504.01399 ↗First posted 2 Apr 2025cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent targets of security threats. Adversarial attacks, first rigorously defined by Ian Goodfellow et al. in 2013, highlight a critical vulnerability: they can trick machine learning models into making incorrect predictions by applying nearly invisible perturbations to images. Although many studies have focused on constructing sophisticated defensive mechanisms to mitigate such attacks, they often overlook the substantial time and computational costs of training and maintaining these models. Ideally, a defense method should be able to generalize across various, even unseen, adversarial attacks with minimal overhead. Building on our previous work on image-to-image translation-based defenses, this study introduces an improved model that incorporates residual blocks to enhance generalizability. The proposed method requires training only a single model, effectively defends against diverse attack types, and is well-transferable between different target models. Experiments show that our model can restore the classification accuracy from near zero to an average of 72% while maintaining competitive performance compared to state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 55 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

41 of 55 references.

References · 41

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  9. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  12. 2014Conditional Generative Adversarial Netscited by 2,162
29 more
  1. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  2. 2016Adversarial examples in the physical worldcited by 1,769
  3. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2016Adversarial Machine Learning at Scalecited by 936
  8. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  9. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  10. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  11. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  12. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  13. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  14. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  15. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  16. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  17. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  18. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
  19. 2018Adversarial Logit Pairingcited by 224
  20. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  21. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 124
  22. 2018Deflecting Adversarial Attacks with Pixel Deflectioncited by 71
  23. 2019Image Super-Resolution as a Defense Against Adversarial Attackscited by 65
  24. 2022When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecturecited by 64
  25. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 34
  26. 2023Generalizable Black-Box Adversarial Attack with Meta Learningcited by 29
  27. 2020A New Perspective on Stabilizing GANs training: Direct Adversarial Trainingcited by 12
  28. 2021Interpolated Joint Space Adversarial Training for Robust and Generalizable Defensescited by 10
  29. 2024Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attackscited by 5

Built on by

Not cited yet.