Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR

Abstract

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.

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Explaining and Harnessing Adversarial Examples
• Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
• Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark
• AI Security for Geoscience and Remote Sensing: Challenges and Future Trends
• Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective
• Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense
• Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition
• Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
• Backpropagating Linearly Improves Transferability of Adversarial Examples
• Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights
• Adversarial Attack across Datasets
• Concealed Electronic Countermeasures of Radar Signal with Adversarial Examples

Cited by in corpus (1)

• Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture