IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
Not on the map. Why?
Abstract (arXiv)
We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical transformation. The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks. To validate this concept, we present a comprehensive study on leveraging image resampling to defend against adversarial attacks. We have developed basic resampling methods that employ interpolation strategies and coordinate shifting magnitudes. Our analysis reveals that these basic methods can partially mitigate adversarial attacks. However, they come with apparent limitations: the accuracy of clean images noticeably decreases, while the improvement in accuracy on adversarial examples is not substantial. We propose implicit representation-driven image resampling (IRAD) to overcome these limitations. First, we construct an implicit continuous representation that enables us to represent any input image within a continuous coordinate space. Second, we introduce SampleNet, which automatically generates pixel-wise shifts for resampling in response to different inputs. Furthermore, we can extend our approach to the state-of-the-art diffusion-based method, accelerating it with fewer time steps while preserving its defense capability. Extensive experiments demonstrate that our method significantly enhances the adversarial robustness of diverse deep models against various attacks while maintaining high accuracy on clean images.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 83 of its 107 references that are in the map. First posted on arXiv 18 Oct 2023.
Builds on
83 of 107 references.
References · 83
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Wide Residual Networkscited by 3,057
- 2016Adversarial examples in the physical worldcited by 1,762
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
- 2020Fast is better than free: Revisiting adversarial trainingcited by 723
38 more
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
- 2019Adversarial Training for Free!cited by 638
- 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
- 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2020Overfitting in adversarially robust deep learningcited by 504
- 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
- 2022Diffusion Models for Adversarial Purificationcited by 469
- 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
- 2017Mitigating Adversarial Effects Through Randomizationcited by 382
- 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
- 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
- 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
- 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
- 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
- 2021Improving Robustness using Generated Datacited by 233
- 2020Understanding and Improving Fast Adversarial Trainingcited by 213
- 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
- 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
- 2020Bag of Tricks for Adversarial Trainingcited by 199
- 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
- 2016A study of the effect of JPG compression on adversarial imagescited by 196
- 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
- 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
- 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
- 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
- 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 155
- 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
- 2019Adversarial Robustness through Local Linearizationcited by 146
- 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
- 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
- 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
- 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
- 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
- 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
50 most cited of 83 All 83 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.