Physical adversarial attack meets computer vision: A decade survey

H Wei, H Tang, X Jia, Z Wang, H Yu, Z Li… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision,
their vulnerability to adversarial attacks remains a critical concern. Extensive research has …

A survey on physical adversarial attack in computer vision

D Wang, W Yao, T Jiang, G Tang, X Chen - arxiv preprint arxiv …, 2022 - arxiv.org
Over the past decade, deep learning has revolutionized conventional tasks that rely on hand-
craft feature extraction with its strong feature learning capability, leading to substantial …

Multiview robust adversarial stickers for arbitrary objects in the physical world

S Oslund, C Washington, A So… - … of Computational and …, 2022 - ojs.bonviewpress.com
Multiview Robust Adversarial Stickers for Arbitrary Objects in the Physical World Page 1
Received: 13 July 2022 | Revised: 18 July 2022 | Accepted: 24 August 2022 | Published online …

Benchmarking adversarial patch against aerial detection

J Lian, S Mei, S Zhang, M Ma - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Deep neural networks (DNNs) have become essential for aerial detection. However, DNNs
are vulnerable to adversarial examples, which pose great security concerns for security …

Adversarial patch attack on multi-scale object detection for UAV remote sensing images

Y Zhang, Y Zhang, J Qi, K Bin, H Wen, X Tong… - Remote Sensing, 2022 - mdpi.com
Although deep learning has received extensive attention and achieved excellent
performance in various scenarios, it suffers from adversarial examples to some extent. In …

CBA: Contextual background attack against optical aerial detection in the physical world

J Lian, X Wang, Y Su, M Ma… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Patch-based physical attacks have increasingly aroused concerns. However, most existing
methods focus on obscuring targets captured on the ground, and some of these methods are …

Adversarial patch attacks against aerial imagery object detectors

G Tang, T Jiang, W Zhou, C Li, W Yao, Y Zhao - Neurocomputing, 2023 - Elsevier
Abstract Although Deep Neural Networks (DNNs)-based object detectors are widely used in
various fields, especially on aerial imagery object detections, it has been observed that a …

A comprehensive study on the robustness of deep learning-based image classification and object detection in remote sensing: Surveying and benchmarking

S Mei, J Lian, X Wang, Y Su, M Ma… - Journal of Remote …, 2024 - spj.science.org
Deep neural networks (DNNs) have found widespread applications in interpreting remote
sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are …

Schemes of attacks on machine learning models

D Namiot - International Journal of Open Information Technologies, 2023 - injoit.ru
This article discusses attack schemes on artificial intelligence systems (on machine learning
models). Classically, attacks on machine learning systems are special data modifications at …

Boosting transferability of physical attack against detectors by redistributing separable attention

Y Zhang, Z Gong, Y Zhang, K Bin, Y Li, J Qi, H Wen… - Pattern Recognition, 2023 - Elsevier
The research on attack transferability is of great importance as it can guide how to conduct
an adversarial attack without knowing any information about target models. However, it …