Advancing Adversarial Training by Injecting Booster Signal
Not on the map. Why?
Abstract (arXiv)
Recent works have demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarial attacks. To defend against adversarial attacks, many defense strategies have been proposed, among which adversarial training has been demonstrated to be the most effective strategy. However, it has been known that adversarial training sometimes hurts natural accuracy. Then, many works focus on optimizing model parameters to handle the problem. Different from the previous approaches, in this paper, we propose a new approach to improve the adversarial robustness by using an external signal rather than model parameters. In the proposed method, a well-optimized universal external signal called a booster signal is injected into the outside of the image which does not overlap with the original content. Then, it boosts both adversarial robustness and natural accuracy. The booster signal is optimized in parallel to model parameters step by step collaboratively. Experimental results show that the booster signal can improve both the natural and robust accuracies over the recent state-of-the-art adversarial training methods. Also, optimizing the booster signal is general and flexible enough to be adopted on any existing adversarial training methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 27 Jun 2023.
Builds on
44 of 63 references.
References · 44
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2016Wide Residual Networkscited by 3,057
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 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
- 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,046
- 2020Fast is better than free: Revisiting adversarial trainingcited by 723
32 more
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
- 2017Mitigating Adversarial Effects Through Randomizationcited by 382
- 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
- 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
- 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
- 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
- 2018Adversarial Logit Pairingcited by 224
- 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
- 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
- 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
- 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
- 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 98
- 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
- 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 85
- 2019A Tensorized Transformer for Language Modelingcited by 85
- 2020Streaming automatic speech recognition with the transformer modelcited by 73
- 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
- 2017Defense against Universal Adversarial Perturbationscited by 48
- 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
- 2022Lip to Speech Synthesis with Visual Context Attentional GANcited by 41
- 2019What it Thinks is Important is Important: Robustness Transfers through Input Gradientscited by 34
- 2019Adversarial Attack on Skeleton-based Human Action Recognitioncited by 32
- 2020Block-wise Image Transformation with Secret Key for Adversarially Robust Defensecited by 30
- 2020A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learningcited by 13
- 2019Black-Box Decision based Adversarial Attack with Symmetric α-stable Distributioncited by 5
- 2020Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attackcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.