Next Article in Journal
Detection of Aguadas (Ponds) Through Remote Sensing in the Bajo El Laberinto Region, Calakmul, Campeche, Mexico
Previous Article in Journal
Integrating Sentinel-1/2 Imagery and Climate Reanalysis for Monthly Bare Soil Mapping and Wind Erosion Modeling in Shandong Province, China
Previous Article in Special Issue
Harmonization of Gaofen-1/WFV Imagery with the HLS Dataset Using Conditional Generative Adversarial Networks
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Remote Sensing
Volume 17
Issue 19
10.3390/rs17193300
remotesensing-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

CAGMC-Defence: A Cross-Attention-Guided Multimodal Collaborative Defence Method for Multimodal Remote Sensing Image Target Recognition

by
Jiahao Cui
1,
Hang Cao
1,
Lingquan Meng
1,
Wang Guo
1,
Keyi Zhang
1,
Qi Wang
1,
Cheng Chang
2,* and
Haifeng Li
1
1
School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
2
Research and Development Centre, China Academy of Launch Vehicle Technology, Beijing 100076, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2025, 17(19), 3300; https://doi.org/10.3390/rs17193300 (registering DOI)
Submission received: 9 July 2025 / Revised: 19 September 2025 / Accepted: 24 September 2025 / Published: 25 September 2025
(This article belongs to the Special Issue Advances in Multimodal Remote Sensing Data: Processing, Fusion and Applications)
Versions Notes

Abstract

With the increasing diversity of remote sensing modalities, multimodal image fusion improves target recognition accuracy but also introduces new security risks. Adversaries can inject small, imperceptible perturbations into a single modality to mislead model predictions, which undermines system reliability. Most existing defences are designed for single-modal inputs and face two key challenges in multimodal settings: 1. vulnerability to perturbation propagation due to static fusion strategies, and 2. the lack of collaborative mechanisms that limit overall robustness according to the weakest modality. To address these issues, we propose CAGMC-Defence, a cross-attention-guided multimodal collaborative defence framework for multimodal remote sensing. It contains two main modules. The Multimodal Feature Enhancement and Fusion (MFEF) module adopts a pseudo-Siamese network and cross-attention to decouple features, capture intermodal dependencies, and suppress perturbation propagation through weighted regulation and consistency alignment. The Multimodal Adversarial Training (MAT) module jointly generates optical and SAR adversarial examples and optimizes network parameters under consistency loss, enhancing robustness and generalization. Experiments on the WHU-OPT-SAR dataset show that CAGMC-Defence maintains stable performance under various typical adversarial attacks, such as FGSM, PGD, and MIM, retaining 85.74% overall accuracy even under the strongest white-box MIM attack (ϵ=0.05), significantly outperforming existing multimodal defence baselines.
Keywords: multimodal remote sensing; adversarial defence; cross-attention mechanism; collaborative defence; adversarial training multimodal remote sensing; adversarial defence; cross-attention mechanism; collaborative defence; adversarial training

Share and Cite

MDPI and ACS Style

Cui, J.; Cao, H.; Meng, L.; Guo, W.; Zhang, K.; Wang, Q.; Chang, C.; Li, H. CAGMC-Defence: A Cross-Attention-Guided Multimodal Collaborative Defence Method for Multimodal Remote Sensing Image Target Recognition. Remote Sens. 2025, 17, 3300. https://doi.org/10.3390/rs17193300

AMA Style

Cui J, Cao H, Meng L, Guo W, Zhang K, Wang Q, Chang C, Li H. CAGMC-Defence: A Cross-Attention-Guided Multimodal Collaborative Defence Method for Multimodal Remote Sensing Image Target Recognition. Remote Sensing. 2025; 17(19):3300. https://doi.org/10.3390/rs17193300

Chicago/Turabian Style

Cui, Jiahao, Hang Cao, Lingquan Meng, Wang Guo, Keyi Zhang, Qi Wang, Cheng Chang, and Haifeng Li. 2025. "CAGMC-Defence: A Cross-Attention-Guided Multimodal Collaborative Defence Method for Multimodal Remote Sensing Image Target Recognition" Remote Sensing 17, no. 19: 3300. https://doi.org/10.3390/rs17193300

APA Style

Cui, J., Cao, H., Meng, L., Guo, W., Zhang, K., Wang, Q., Chang, C., & Li, H. (2025). CAGMC-Defence: A Cross-Attention-Guided Multimodal Collaborative Defence Method for Multimodal Remote Sensing Image Target Recognition. Remote Sensing, 17(19), 3300. https://doi.org/10.3390/rs17193300

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop