Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example Transferability

The vulnerability of synthetic aperture radar (SAR)—automatic target recognition (ATR) models based on deep neural networks has garnered increasing attention in recent research. A novel and extreme prior-knowledge-limited attack scenario, synthetic-to-measured (S2M), has been proposed, wh...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaying Jin, Shuangju Zhou, Chenyu Wang, Mingxin Fu, Quan Pan, Yang Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11039638/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428696470913024
author Xiaying Jin
Shuangju Zhou
Chenyu Wang
Mingxin Fu
Quan Pan
Yang Li
author_facet Xiaying Jin
Shuangju Zhou
Chenyu Wang
Mingxin Fu
Quan Pan
Yang Li
author_sort Xiaying Jin
collection DOAJ
description The vulnerability of synthetic aperture radar (SAR)—automatic target recognition (ATR) models based on deep neural networks has garnered increasing attention in recent research. A novel and extreme prior-knowledge-limited attack scenario, synthetic-to-measured (S2M), has been proposed, where the architecture, parameters, training data, and outputs of the target model remain entirely unknown, and adversarial perturbations are generated exclusively using synthetic data. To address the challenges posed by the S2M attack scenario, we propose FUA, a comprehensive framework to improve the transferability of adversarial examples generated by SAR-ATR surrogate models. By introducing an S2M transferability estimation between the surrogate and target models, FUA progressively optimizes the surrogate model from three aspects: model parameters, data distribution, and model architecture. First, fine-tuning phase provides the suitable initial model parameters. Then, uniform data distribution fine-tuning phase generates a uniform substitute dataset with a decision boundary smoothing loss to further fine-tune the surrogate model. Finally, Architecture modification phase modifies the activation functions and skip connections of the model architecture with the parameters fixed. Experimental results demonstrate that FUA can outperform SOTA methods and significantly improve the S2M transferability across various adversarial attack algorithms. The optimization strategies at each phase can contribute to overall performance improvements.
format Article
id doaj-art-577ba26b2b464504ab7fdbb82af6b293
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-577ba26b2b464504ab7fdbb82af6b2932025-08-20T03:28:37ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118162461625610.1109/JSTARS.2025.358096311039638Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example TransferabilityXiaying Jin0Shuangju Zhou1Chenyu Wang2https://orcid.org/0009-0007-0510-3307Mingxin Fu3Quan Pan4https://orcid.org/0000-0001-8162-2896Yang Li5https://orcid.org/0000-0001-5672-4110School of Cyberspace Security, Northwestern Polytechnical University, Xi’an, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an, ChinaThe vulnerability of synthetic aperture radar (SAR)—automatic target recognition (ATR) models based on deep neural networks has garnered increasing attention in recent research. A novel and extreme prior-knowledge-limited attack scenario, synthetic-to-measured (S2M), has been proposed, where the architecture, parameters, training data, and outputs of the target model remain entirely unknown, and adversarial perturbations are generated exclusively using synthetic data. To address the challenges posed by the S2M attack scenario, we propose FUA, a comprehensive framework to improve the transferability of adversarial examples generated by SAR-ATR surrogate models. By introducing an S2M transferability estimation between the surrogate and target models, FUA progressively optimizes the surrogate model from three aspects: model parameters, data distribution, and model architecture. First, fine-tuning phase provides the suitable initial model parameters. Then, uniform data distribution fine-tuning phase generates a uniform substitute dataset with a decision boundary smoothing loss to further fine-tune the surrogate model. Finally, Architecture modification phase modifies the activation functions and skip connections of the model architecture with the parameters fixed. Experimental results demonstrate that FUA can outperform SOTA methods and significantly improve the S2M transferability across various adversarial attack algorithms. The optimization strategies at each phase can contribute to overall performance improvements.https://ieeexplore.ieee.org/document/11039638/Adversarial attackblack box attacksynthetic aperture radar (SAR)transfer attack
spellingShingle Xiaying Jin
Shuangju Zhou
Chenyu Wang
Mingxin Fu
Quan Pan
Yang Li
Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example Transferability
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Adversarial attack
black box attack
synthetic aperture radar (SAR)
transfer attack
title Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example Transferability
title_full Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example Transferability
title_fullStr Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example Transferability
title_full_unstemmed Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example Transferability
title_short Enhancing SAR-ATR Systems’ Resistance to S2M Attacks via FUA: Optimizing Surrogate Models for Adversarial Example Transferability
title_sort enhancing sar atr systems x2019 resistance to s2m attacks via fua optimizing surrogate models for adversarial example transferability
topic Adversarial attack
black box attack
synthetic aperture radar (SAR)
transfer attack
url https://ieeexplore.ieee.org/document/11039638/
work_keys_str_mv AT xiayingjin enhancingsaratrsystemsx2019resistancetos2mattacksviafuaoptimizingsurrogatemodelsforadversarialexampletransferability
AT shuangjuzhou enhancingsaratrsystemsx2019resistancetos2mattacksviafuaoptimizingsurrogatemodelsforadversarialexampletransferability
AT chenyuwang enhancingsaratrsystemsx2019resistancetos2mattacksviafuaoptimizingsurrogatemodelsforadversarialexampletransferability
AT mingxinfu enhancingsaratrsystemsx2019resistancetos2mattacksviafuaoptimizingsurrogatemodelsforadversarialexampletransferability
AT quanpan enhancingsaratrsystemsx2019resistancetos2mattacksviafuaoptimizingsurrogatemodelsforadversarialexampletransferability
AT yangli enhancingsaratrsystemsx2019resistancetos2mattacksviafuaoptimizingsurrogatemodelsforadversarialexampletransferability