CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12538 > Article
Paper
12 June 2023 Adversarial attack on GNN-based SAR image classifier
Tian Ye, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Author Affiliations +
Proceedings Volume 12538, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V; 1253812 (2023) https://doi.org/10.1117/12.2666030
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States
Abstract
Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is a key technique in remote-sensing image recognition. The state-of-the-art Graph Neural Network (GNN) has achieved 99.09% accuracy on the MSTAR dataset. However, robustness is a critical concern when an adversary can add carefully crafted noise to the test image and mislead the classifier to give wrong output. In this work, we study the vulnerability of the state-of-the-art GNN-based SAR image classifier and show the feasibility of decreasing its accuracy by manipulating test images using the Fast Gradient Sign Method (FGSM). The intuition is that misclassifications are more likely to occur when the loss is high. For each SAR image, we add noise to every pixel, such that the perturbed image will be misclassified by the GNN model. For each pixel, the noise is determined by the gradient of the loss with respect to the pixel. Also, we guarantee that the noise values are sufficiently small such that the perturbation will be unnoticeable to human eyes. We conduct experiments by applying the attack on the 2425 test images from the MSTAR dataset. In our experiments, the accuracy of the target GNN drastically drops from 99.09% to 11.79% after we change each normalized pixel value (in [0, 1]) of the test images by less than 3/255.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Tian Ye, Rajgopal Kannan, Viktor Prasanna, and Carl Busart "Adversarial attack on GNN-based SAR image classifier", Proc. SPIE 12538, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V, 1253812 (12 June 2023); https://doi.org/10.1117/12.2666030
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
;
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 5 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Synthetic aperture radar
Image classification
Automatic target recognition
Defense and security
Machine learning
Neural networks
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top