Document Type
Article
Publication Date
2026
DOI
10.3390/electronics15204610
Publication Title
Electronics
Volume
15
Issue
20
Pages
4610 (23 pp)
Abstract
We investigate the vulnerability of multi-task maritime surveillance systems in which object detection and semantic segmentation operate concurrently. We propose Stabilized Multi-Objective Optimization (SMO), a framework that jointly targets Mask R-CNN and U-Net with a single universal adversarial texture in a digital white-box setting, with additional cross-model transfer evaluation. SMO combines a logarithmic-inversion loss transformation, feature inconsistency, and a systematic comparison of six optimization strategies for seven heterogeneous objectives. The loss transformation controls loss-dependent gradient scaling, while a U-Net generator supplies a spatially coherent texture and a hull-aligned application function accommodates target geometry without explicit Expectation over Transformation (EoT) sampling. Experiments on Airbus Ship Detection, Dataset for Object Detection in Aerial Images (DOTA), and Vision Meets Drone (VisDrone) demonstrate substantial reductions in average precision (AP) and mean intersection over union (mIoU). Together, these results demonstrate the effectiveness of SMO’s joint optimization framework in generating a single adversarial texture that disrupts heterogeneous detection and segmentation models, revealing vulnerabilities in integrated remote-sensing perception systems.
Rights
© 2026 by the authors.
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution 4.0 International (CC BY 4.0) License.
Data Availability
Article states: "The data presented in this study are openly available in Airbus at https://www.kaggle.com/competitions/airbus-ship-detection (accessed on 5 August 2025)."
Original Publication Citation
Rajabi Rostami, O., Islam, K. A., Zhu, L., Ning, R., Xin, C., Wu, H., & Li, J. (2026). Stabilized multi-objective optimization for camouflage attack in remote sensing. Electronics, 15(20), Article 4610. https://doi.org/10.3390/electronics15204610
Repository Citation
Rostami, Omid Rajabi; Islam, Kazi Aminul; Zhu, Liuwan; Ning, Rui; Xin, Chungsheng; Wu, Hongyi; and Li, Jiang, "Stabilized Multi-Objective Optimization for Camouflage Attack in Remote Sensing" (2026). Electrical & Computer Engineering Faculty Publications. 616.
https://digitalcommons.odu.edu/ece_fac_pubs/616
ORCID
0000-0002-3641-9714 (Rostami), 0000-0003-0091-6986 (Li)
Included in
Artificial Intelligence and Robotics Commons, Cybersecurity Commons, Electrical and Computer Engineering Commons