CamoNet: A target camouflage network for remote sensing images based on adversarial attack

Y Zhou, W Jiang, X Jiang, L Chen, X Liu - Remote Sensing, 2023 - mdpi.com
Object detection algorithms based on convolutional neural networks (CNNs) have achieved
remarkable success in remote sensing images (RSIs), such as aircraft and ship detection …

Adversarial attacks in computer vision: a survey

C Li, H Wang, W Yao, T Jiang - Journal of Membrane Computing, 2024 - Springer
Deep learning, as an important topic of artificial intelligence, has been widely applied in
various fields, especially in computer vision applications, such as image classification and …

Towards Robust Physical-world Backdoor Attacks on Lane Detection

X Zhang, A Liu, T Zhang, S Liang, X Liu - arXiv preprint arXiv:2405.05553, 2024 - arxiv.org
Deep learning-based lane detection (LD) plays a critical role in autonomous driving
systems, such as adaptive cruise control. However, it is vulnerable to backdoor attacks …

Empowering Physical Attacks with Jacobian Matrix Regularization against ViT-based Detectors in UAV Remote Sensing Images

Y Zhang, Z Gong, W Liu, H Wen, P Wan… - … on Geoscience and …, 2024 - ieeexplore.ieee.org
Vision Transformers (ViTs) have achieved great success in UAV target detection tasks.
However, little attention has been paid to the adversarial attack against ViT-based detectors …

Pattern Corruption-Assisted Physical Attacks Against Object Detection in UAV Remote Sensing

Y Zhang, Z Gong, H Wen, X Hu, X Xia… - IEEE Journal of …, 2024 - ieeexplore.ieee.org
Deep Neural Networks (DNNs) have attained remarkable success in aerial detection tasks,
yet they remain susceptible to adversarial samples, posing a significant challenge for their …

Physical Strip Attack for Object Detection in Optical Remote Sensing

C Sun, J Sun, X Zhang, Y Li, Q Bai… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
A growing trend in the field of adversarial attacks is evolving from the digital domain to the
more challenging physical domain. The previous works mainly employ printable adversarial …