Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR
Not on the map. Why?
Abstract (arXiv)
Recently, there has been increasing concern about the vulnerability of deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) to adversarial attacks, where a DNN could be easily deceived by clean input with imperceptible but aggressive perturbations. This paper studies the synthetic-to-measured (S2M) transfer setting, where an attacker generates adversarial perturbation based solely on synthetic data and transfers it against victim models trained with measured data. Compared with the current measured-to-measured (M2M) transfer setting, our approach does not need direct access to the victim model or the measured SAR data. We also propose the transferability estimation attack (TEA) to uncover the adversarial risks in this more challenging and practical scenario. The TEA makes full use of the limited similarity between the synthetic and measured data pairs for blind estimation and optimization of S2M transferability, leading to feasible surrogate model enhancement without mastering the victim model and data. Comprehensive evaluations based on the publicly available synthetic and measured paired labeled experiment (SAMPLE) dataset demonstrate that the TEA outperforms state-of-the-art methods and can significantly enhance various attack algorithms in computer vision and remote sensing applications. Codes and data are available at https://github.com/scenarri/S2M-TEA.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 40 of its 90 references that are in the map. First posted on arXiv 30 Jan 2024.
Builds on
40 of 90 references.
References · 40
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2016Adversarial examples in the physical worldcited by 1,762
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
- 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
28 more
- 2020Designing Network Design Spacescited by 954
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
- 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
- 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
- 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
- 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
- 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
- 2017Generative Adversarial Perturbationscited by 153
- 2019Cross-Domain Transferability of Adversarial Perturbationscited by 92
- 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
- 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
- 2020Understanding Adversarial Examples from the Mutual Influence of Images and Perturbationscited by 59
- 2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
- 2021TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothnesscited by 37
- 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 36
- 2021A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attackscited by 33
- 2023Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabilitycited by 32
- 2020Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustnesscited by 28
- 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
- 2020Adversarial Examples on Object Recognition: A Comprehensive Surveycited by 23
- 2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
- 2020Automatic Target Recognition on Synthetic Aperture Radar Imagery: A Surveycited by 18
- 2022Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defensecited by 14
- 2023Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognitioncited by 6
- 2023Physics Inspired Hybrid Attention for SAR Target Recognitioncited by 6
- 2023Crucial Feature Capture and Discrimination for Limited Training Data SAR ATRcited by 4
- 2021Adversarial Attack across Datasetscited by 2
- 2023Concealed Electronic Countermeasures of Radar Signal with Adversarial Examplescited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.