mlsanityData to 7 Oct 2026

Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense

arXiv 2209.04779 ↗First posted 11 Sep 2022cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) based Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems have shown to be highly vulnerable to adversarial perturbations that are deliberately designed yet almost imperceptible but can bias DNN inference when added to targeted objects. This leads to serious safety concerns when applying DNNs to high-stake SAR ATR applications. Therefore, enhancing the adversarial robustness of DNNs is essential for implementing DNNs to modern real-world SAR ATR systems. Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers). The proposed SMGAA consists of two parts: 1) a parametric scattering model and corresponding imaging method and 2) a customized gradient-based optimization algorithm. First, we introduce the effective Attributed Scattering Center Model (ASCM) and a general imaging method to describe the scattering behavior of typical geometric structures in the SAR imaging process. By further devising several strategies to take the domain knowledge of SAR target images into account and relax the greedy search procedure, the proposed method does not need to be prudentially finetuned, but can efficiently to find the effective ASCM parameters to fool the SAR classifiers and facilitate the robust model training. Comprehensive evaluations on the MSTAR dataset show that the adversarial scatterers generated by SMGAA are more robust to perturbations and transformations in the SAR processing chain than the currently studied attacks, and are effective to construct a defensive model against the malicious scatterers.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 37 of its 75 references that are in the map. First posted on arXiv 11 Sep 2022.

Builds on

37 of 75 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
25 more
  1. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  2. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  3. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  4. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  5. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  6. 2017Countering Adversarial Images using Input Transformationscited by 517
  7. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  8. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  9. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  10. 2018LaVAN: Localized and Visible Adversarial Noisecited by 112
  11. 2019Sparse and Imperceivable Adversarial Attackscited by 95
  12. 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
  13. 2019Functional Adversarial Attackscited by 82
  14. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  15. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  16. 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
  17. 2020Deep Learning Meets SARcited by 60
  18. 2020Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effectcited by 40
  19. 2018Invisible Mask: Practical Attacks on Face Recognition with Infraredcited by 33
  20. 2020Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustnesscited by 28
  21. 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
  22. 2020Automatic Target Recognition on Synthetic Aperture Radar Imagery: A Surveycited by 18
  23. 2021Universal Spectral Adversarial Attacks for Deformable Shapescited by 14
  24. 2022Attentional Feature Refinement and Alignment Network for Aircraft Detection in SAR Imagerycited by 7
  25. 2018Texture Classification in Extreme Scale Variations using GANetcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 5; 2025: 0; 2026: 1.

14 papers.

Sort:

By area:

  1. 2024SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detectioncited by 47
  2. 2023Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecturecited by 43
  3. 2024SARATR-X: Toward Building A Foundation Model for SAR Target Recognitioncited by 25
  4. 2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
  5. 2023Discovering and Explaining the Non-Causality of Deep Learning in SAR ATRcited by 9
  6. 2023Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognitioncited by 6
  7. 2023Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Modelscited by 5
  8. 2023Realistic Scatterer Based Adversarial Attacks on SAR Image Classifierscited by 5
  9. 2024Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATRcited by 1
  10. 2023Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognitioncited by 0
  11. 2023Background Debiased SAR Target Recognition via Causal Interventional Regularizercited by 0
  12. 2024SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameterscited by 0
2 more
  1. 2024Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networkscited by 0
  2. 2026Towards Physically Realizable Adversarial Attenuation Patch against SAR Object Detectioncited by 0