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

by   Bowen Peng, et al.

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.


page 1

page 2

page 7

page 9

page 10

page 12

page 13

page 14


Adversarial Example Defense via Perturbation Grading Strategy

Deep Neural Networks have been widely used in many fields. However, stud...

Differentiable SAR Renderer and SAR Target Reconstruction

Forward modeling of wave scattering and radar imaging mechanisms is the ...

Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition

The deep neural networks (DNNs) have freed the synthetic aperture radar ...

A Spectral Perspective towards Understanding and Improving Adversarial Robustness

Deep neural networks (DNNs) are incredibly vulnerable to crafted, imperc...

SAR-NeRF: Neural Radiance Fields for Synthetic Aperture Radar Multi-View Representation

SAR images are highly sensitive to observation configurations, and they ...

Explainable, Physics Aware, Trustworthy AI Paradigm Shift for Synthetic Aperture Radar

The recognition or understanding of the scenes observed with a SAR syste...

Through-the-Wall Nonlinear SAR Imaging

An inverse scattering problem for SAR data in application to through-the...

Please sign up or login with your details

Forgot password? Click here to reset