Adversarial deep learning: A survey on adversarial attacks and defense mechanisms on image classification

SY Khamaiseh, D Bagagem, A Al-Alaj… - IEEE …, 2022 - ieeexplore.ieee.org
The popularity of adapting deep neural networks (DNNs) in solving hard problems has
increased substantially. Specifically, in the field of computer vision, DNNs are becoming a …

Universal adversarial attacks on deep neural networks for medical image classification

H Hirano, A Minagi, K Takemoto - BMC medical imaging, 2021 - Springer
Abstract Background Deep neural networks (DNNs) are widely investigated in medical
image classification to achieve automated support for clinical diagnosis. It is necessary to …

Attacking deep reinforcement learning with decoupled adversarial policy

K Mo, W Tang, J Li, X Yuan - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
While Deep Reinforcement Learning (DRL) has achieved outstanding performance in
extensive applications, exploiting its vulnerability with adversarial attacks is essential …

Adversarial robustness assessment: Why in evaluation both L0 and L attacks are necessary

S Kotyan, DV Vargas - PLoS One, 2022 - journals.plos.org
There are different types of adversarial attacks and defences for machine learning
algorithms which makes assessing the robustness of an algorithm a daunting task …

Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks

H Hirano, K Koga, K Takemoto - Plos one, 2020 - journals.plos.org
Owing the epidemic of the novel coronavirus disease 2019 (COVID-19), chest X-ray
computed tomography imaging is being used for effectively screening COVID-19 patients …

Universal adversarial perturbations for CNN classifiers in EEG-based BCIs

Z Liu, L Meng, X Zhang, W Fang… - Journal of Neural …, 2021 - iopscience.iop.org
Objective. Multiple convolutional neural network (CNN) classifiers have been proposed for
electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, CNN …

A simple and strong baseline for universal targeted attacks on Siamese visual tracking

Z Li, Y Shi, J Gao, S Wang, B Li… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Siamese trackers are shown to be vulnerable to adversarial attacks recently. However, the
existing attack methods craft the perturbations for each video independently, which comes at …

Natural images allow universal adversarial attacks on medical image classification using deep neural networks with transfer learning

A Minagi, H Hirano, K Takemoto - Journal of Imaging, 2022 - mdpi.com
Transfer learning from natural images is used in deep neural networks (DNNs) for medical
image classification to achieve a computer-aided clinical diagnosis. Although the …

Backdoor attacks to deep neural network-based system for COVID-19 detection from chest X-ray images

Y Matsuo, K Takemoto - Applied Sciences, 2021 - mdpi.com
Open-source deep neural networks (DNNs) for medical imaging are significant in emergent
situations, such as during the pandemic of the 2019 novel coronavirus disease (COVID-19) …

A reading survey on adversarial machine learning: Adversarial attacks and their understanding

S Kotyan - arxiv preprint arxiv:2308.03363, 2023 - arxiv.org
Deep Learning has empowered us to train neural networks for complex data with high
performance. However, with the growing research, several vulnerabilities in neural networks …