Boosting Adversarial Robustness and Generalization with Dictionary Structure
Not on the map. Why?
Abstract (arXiv)
This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically, our study surprisingly reveals that existing dictionary learning-inspired convolutional neural networks (CNNs) are robust against random noise but remain highly vulnerable to adversarial attacks. To address this, we propose Elastic Dictionary Learning Networks (EDLNets), a novel ResNet architecture that significantly enhances adversarial robustness and generalization. Extensive and reliable experiments demonstrate consistent improvements in adversarial robustness across multiple datasets, backbone architectures, and threat models. To the best of our knowledge, this is the first work to discover and validate that dictionary structure can reliably enhance deep learning robustness under strong adaptive attacks, unveiling a promising direction for future research.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 69 references that are in the map. First posted on arXiv 2 Feb 2025.
Builds on
45 of 69 references.
References · 45
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 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
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
33 more
- 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
- 2020Overfitting in adversarially robust deep learningcited by 504
- 2022Diffusion Models for Adversarial Purificationcited by 469
- 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
- 2017Detecting Adversarial Samples from Artifactscited by 244
- 2021Improving Robustness using Generated Datacited by 233
- 2017On Detecting Adversarial Perturbationscited by 232
- 2020Understanding and Improving Fast Adversarial Trainingcited by 213
- 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
- 2017On the (Statistical) Detection of Adversarial Examplescited by 180
- 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
- 2019Adversarial Robustness through Local Linearizationcited by 146
- 2021Adversarial purification with Score-based generative modelscited by 132
- 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
- 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
- 2018SparseFool: a few pixels make a big differencecited by 94
- 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
- 2019Adversarially Robust Generalization Just Requires More Unlabeled Datacited by 75
- 2020Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defensescited by 61
- 2016Convolutional Neural Networks Analyzed via Convolutional Sparse Codingcited by 51
- 2021Consistency Regularization for Adversarial Robustnesscited by 42
- 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
- 2023WAT: Improve the Worst-class Robustness in Adversarial Trainingcited by 27
- 2022Scaling Adversarial Training to Large Perturbation Boundscited by 20
- 2020Architectural Adversarial Robustness: The Case for Deep Pursuitcited by 18
- 2022Revisiting Sparse Convolutional Model for Visual Recognitioncited by 13
- 2018Deep Dictionary Learning: A PARametric NETwork Approachcited by 12
- 2023Robust Graph Neural Networks via Unbiased Aggregationcited by 8
- 2024ProTransformer: Robustify Transformers via Plug-and-Play Paradigmcited by 5
- 2024Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attackscited by 4
- 2024Robustness Reprogramming for Representation Learningcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.