Improving Adversarial Robustness via Decoupled Visual Representation Masking
Not on the map. Why?
Abstract (arXiv)
Deep neural networks are proven to be vulnerable to fine-designed adversarial examples, and adversarial defense algorithms draw more and more attention nowadays. Pre-processing based defense is a major strategy, as well as learning robust feature representation has been proven an effective way to boost generalization. However, existing defense works lack considering different depth-level visual features in the training process. In this paper, we first highlight two novel properties of robust features from the feature distribution perspective: 1) Diversity. The robust feature of intra-class samples can maintain appropriate diversity; 2) Discriminability. The robust feature of inter-class samples should ensure adequate separation. We find that state-of-the-art defense methods aim to address both of these mentioned issues well. It motivates us to increase intra-class variance and decrease inter-class discrepancy simultaneously in adversarial training. Specifically, we propose a simple but effective defense based on decoupled visual representation masking. The designed Decoupled Visual Feature Masking (DFM) block can adaptively disentangle visual discriminative features and non-visual features with diverse mask strategies, while the suitable discarding information can disrupt adversarial noise to improve robustness. Our work provides a generic and easy-to-plugin block unit for any former adversarial training algorithm to achieve better protection integrally. Extensive experimental results prove the proposed method can achieve superior performance compared with state-of-the-art defense approaches. The code is publicly available at hrefhttps://github.com/chenboluo/Adversarial-defensehttps://github.com/chenboluo/Adversarial-defense.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 62 references that are in the map. First posted on arXiv 16 Jun 2024.
Builds on
38 of 62 references.
References · 38
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2017One pixel attack for fooling deep neural networkscited by 582
- 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 379
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
26 more
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
- 2018Spatially Transformed Adversarial Examplescited by 195
- 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 158
- 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
- 2018SparseFool: a few pixels make a big differencecited by 94
- 2023Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous drivingcited by 83
- 2024FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mambacited by 81
- 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
- 2019Who is Real Bob? Adversarial Attacks on Speaker Recognition Systemscited by 67
- 2021PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifiercited by 65
- 2019Training Robust Deep Neural Networks via Adversarial Noise Propagationcited by 62
- 2022Practical Evaluation of Adversarial Robustness via Adaptive Auto Attackcited by 44
- 2021Consistency Regularization for Adversarial Robustnesscited by 42
- 2021GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularizationcited by 34
- 2021Towards Defending against Adversarial Examples via Attack-Invariant Featurescited by 25
- 2022Face Recognition Accuracy Across Demographics: Shining a Light Into the Problemcited by 25
- 2021Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifierscited by 24
- 2021CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selectioncited by 21
- 2022Pixle: a fast and effective black-box attack based on rearranging pixelscited by 20
- 2019Interpreting Adversarial Examples by Activation Promotion and Suppressioncited by 17
- 2021Stereoscopic Universal Perturbations across Different Architectures and Datasetscited by 17
- 2022Block Hunter: Federated Learning for Cyber Threat Hunting in Blockchain-based IIoT Networkscited by 16
- 2023Feature Separation and Recalibration for Adversarial Robustnesscited by 16
- 2019Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"cited by 12
- 2022A Mask-Based Adversarial Defense Schemecited by 2
- 2021Less is More: Feature Selection for Adversarial Robustness with Compressive Counter-Adversarial Attackscited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.