Adaptive Rotation-Scaling Ensemble Patch Attack for Ship Detection in Remote Sensing Images
Open Access
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 14231-14246
Abstract
Existing adversarial patch generation methods for remote sensing ship detection suffer from several limitations, including insufficient adaptability to patch size, inability to handle orientation variations of rotated ships, and poor transferability of adversarial patches. Considering these problems, this paper first proposes an adaptive rotation-scaling ensemble patch attack method, named ARSEA, to enhance suitability of adversarial patches for ship sizes and orientations. Specifically, a adversarial patch is scaled according to the size of the rotated bounding box of the ship and rotated using the angle information combined with a location-aware mask, enabling precise alignment with ship targets of various sizes and orientations. For the last problem, a model ensemble attack strategy based on gradient direction consistency is proposed, where weights are adaptively assigned according to the cosine similarity between the gradients of multiple surrogate models. This guides the patch optimization toward the commonly vulnerable regions shared by multiple models, reduces gradient conflicts, and enhances the transferability of the patch. Experimental results on multiple datasets demonstrate that the proposed method significantly reduces the detection accuracy of ship targets. When integrating multiple detectors, the generated patch achieves approximately 60% mAP reduction and 50% target vanishing rate on three unknown black-box detection models. Furthermore, in multi-class attack scenarios, the proposed method also achieves an attack success rate of around 40%, showing strong transferability.Keywords
Funding Information
- National Natural Science Foundation of China (42301433)
- Natural Science Foundation of Hainan Province (2024JJ6496)
This publication has 38 references indexed in Scilit:
- Understanding the adversarial robustness of deep learning-based single-pixel imagingPattern Recognition, 2025
- Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks2023
- ROS-Det: Arbitrary-Oriented Ship Detection in High Resolution Optical Remote Sensing Images via Rotated One-Stage DetectorIEEE Access, 2021
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection2020
- Ensemble adversarial black-box attacks against deep learning systemsPattern Recognition, 2020
- Fooling Automated Surveillance Cameras: Adversarial Patches to Attack Person Detection2019
- Learning RoI Transformer for Oriented Object Detection in Aerial Images2019
- ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector2019
- Adversarial Examples for Semantic Segmentation and Object Detection2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016