CBA: Contextual Background Attack Against Optical Aerial Detection in the Physical World

Lian, Jiawei; Wang, Xiaofei; Su, Yuru; Ma, Mingyang; Mei, Shaohui

doi:10.1109/tgrs.2023.3264839

Cited by 19 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, both global attacks and patch-based attacks are easily detected by the naked eye [31,32]. Global attacks are unsuitable for the RSI's object detection because the target only occupies a small area in the RSI [33]. This means the perturbation generated in the background area usually does not improve the attack effect but may add the perturbed pixels and weaken the invisibility.…”

Section: Introductionmentioning

confidence: 99%

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

Zhou,

Jiang,

Jiang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

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).

show abstract

Section: Introductionmentioning

confidence: 99%