EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack

Yue Zhou, Wanghan Jiang, Xue Jiang, Lin Chen, Xingzhao Liu

Remote Sensing · 27.10.2023 · 15 (21) · 5131

DOI: 10.3390/rs15215131 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 27.10.2023. Verfasst von Yue Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object detection algorithms based on convolutional neural networks (CNNs) have achieved remarkable success in remote sensing images (RSIs), such as aircraft and ship detection, which play a vital role in military and civilian fields. However, CNNs are fragile and can be easily fooled. There have been a series of studies on adversarial attacks for image classification in RSIs. However, the existing gradient attack algorithms designed for classification cannot achieve excellent performance when directly applied to object detection, which is an essential task in RSI understanding. Although we can find some works on adversarial attacks for object detection, they are weak in concealment and easily detected by the naked eye. To handle these problems, we propose a target camouflage network for object detection in RSIs, called CamoNet, to deceive CNN-based detectors by adding imperceptible perturbation to the image. In addition, we propose a detection space initialization strategy to maximize the diversity in the detector’s outputs among the generated samples. It can enhance the performance of the gradient attack algorithms in the object detection task. Moreover, a key pixel distillation module is employed, which can further reduce the modified pixels without weakening the concealment effect. Compared with several of the most advanced adversarial attacks, the proposed attack has advantages in terms of both peak signal-to-noise ratio (PSNR) and attack success rate. The transferability of the proposed target camouflage network is evaluated on three dominant detection algorithms (RetinaNet, Faster R-CNN, and RTMDet) with two commonly used remote sensing datasets (i.e., DOTA and DIOR).

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhou, Y., Jiang, W., Jiang, X., Chen, L., & Liu, X. (2023). CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack. Remote Sensing, 15(21), 5131. https://doi.org/10.3390/rs15215131

Vancouver

Zhou Y, Jiang W, Jiang X, Chen L, Liu X. CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack. Remote Sensing. 2023;15(21):5131. doi:10.3390/rs15215131

BibTeX
@article{Zhou2023,
  author = {Zhou, Yue and Jiang, Wanghan and Jiang, Xue and Chen, Lin and Liu, Xingzhao},
  title = {CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {21},
  pages = {5131},
  doi = {10.3390/rs15215131}
}
Kostenlos starten →