Adversarial pan-sharpening attacks for object detection in remote sensing

Xingxing Wei

doi:10.1016/j.patcog.2023.109466

Adversarial pan-sharpening attacks for object detection in remote sensing

2023-07-01

16

PRE

AI

DOI：10.1016/j.patcog.2023.109466

Original

Original request for help

Save

Abstract

En 中文

Pan-sharpening, as one of the most commonly used techniques in remote sensing systems, aims to fuse texture-rich PAN images and multi-spectral MS images to obtain texture-rich MS images. With the devel-opment of deep learning, CNN based Pan-sharpening methods have received more and more attention in recent years. Since Pan-sharpening technique can integrate the complementary information of Pan and MS images, researchers usually apply object detectors on these pan-sharpened images to achieve reliable detection results. However, recent studies have shown that Deep Learning-based object detection meth-ods are vulnerable to adversarial examples, i.e., adding imperceptible noise to clean images can fool well -trained deep neural networks. It is interesting to combine the pan-sharpening technique with adversarial examples to attack object detectors in remote sensing. In this paper, we propose a framework to generate adversarial pan-sharpened images. Specifically, we propose a two-stream network to generate the pan -sharpened images, and then utilize the shape loss and label loss to perform the attack task. To guarantee the quality of pan-sharpened images, a perceptual loss is utilized to balance spectral preservation and at-tacking performance. Experimental results demonstrate that the proposed method can generate effective adversarial pan-sharpened images that maintain a high success rate for white-box attacks and achieve transferability for black-box attacks. (c) 2023 Elsevier Ltd. All rights reserved.

Keywords:

Adversarial pan-sharpening

Remote sensing

Object detection

Adversarial pan-sharpening attacks for object detection in remote sensing

Abstract

Journal

Organization