Query-efficient decision-based black-box patch attack

Z Chen, B Li, S Wu, S Ding… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible
adversarial perturbations. As a complementary type of adversary, patch attacks that …

Towards a robust deep neural network against adversarial texts: A survey

W Wang, R Wang, L Wang, Z Wang… - ieee transactions on …, 2021 - ieeexplore.ieee.org
Deep neural networks (DNNs) have achieved remarkable success in various tasks (eg,
image classification, speech recognition, and natural language processing (NLP)). However …

Restricted black-box adversarial attack against deepfake face swapping

J Dong, Y Wang, J Lai, X Xie - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
DeepFake face swapping presents a significant threat to online security and social media,
which can replace the source face in an arbitrary photo/video with the target face of an …

Decision-based adversarial attack with frequency mixup

XC Li, XY Zhang, F Yin, CL Liu - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
It has been widely observed that deep neural networks are highly vulnerable to adversarial
examples. Decision-based attacks could generate adversarial examples based solely on top …

A novel robustness-enhancing adversarial defense approach to AI-powered sea state estimation for autonomous marine vessels

S Li, X Cheng, F Shi, H Zhang, H Dai… - … on Systems, Man …, 2024 - ieeexplore.ieee.org
Sea state information is significant for the guide of maritime activities of autonomous vessels.
The sea state estimation (SSE) model, powered by artificial intelligence (AI), has shown …

Security issues and defensive approaches in deep learning frameworks

H Chen, Y Zhang, Y Cao, J Xie - Tsinghua Science and …, 2021 - ieeexplore.ieee.org
Deep learning frameworks promote the development of artificial intelligence and
demonstrate considerable potential in numerous applications. However, the security issues …

Towards a robust deep neural network in texts: A survey

W Wang, R Wang, L Wang, Z Wang, A Ye - arXiv preprint arXiv …, 2019 - arxiv.org
Deep neural networks (DNNs) have achieved remarkable success in various tasks (eg,
image classification, speech recognition, and natural language processing (NLP)). However …

Transferable black-box attack against face recognition with spatial mutable adversarial patch

H Ma, K Xu, X Jiang, Z Zhao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Deep Neural Networks (DNNs) are vulnerable to adversarial patch attacks, which raises
security concerns for face recognition systems using DNNs. Previous attack methods focus …

Revisiting gradient regularization: Inject robust saliency-aware weight bias for adversarial defense

Q Li, Q Hu, C Lin, D Wu, C Shen - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Despite regularizing the Jacobians of neural networks to enhance model robustness has
directly theoretical correlation with model prediction stability, a large defense performance …

Adversarial exposure attack on diabetic retinopathy imagery grading

Y Cheng, Q Guo, F Juefei-Xu, H Fu… - IEEE Journal of …, 2024 - ieeexplore.ieee.org
Diabetic Retinopathy (DR) is a leading cause of vision loss around the world. To help
diagnose it, numerous cutting-edge works have built powerful deep neural networks (DNNs) …