Boosting Adversarial Robustness and Generalization with Dictionary Structure
TL;DR
This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models and proposes Elastic Dictionary Learning Networks (EDLNets), a novel ResNet architecture that significantly enhances adversarial robustness and generalization.
Abstract
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.