Adversarial attacks and defenses in machine learning-empowered communication systems and networks: A contemporary survey
Adversarial attacks and defenses in machine learning and deep neural network (DNN) have
been gaining significant attention due to the rapidly growing applications of deep learning in …
been gaining significant attention due to the rapidly growing applications of deep learning in …
A survey of robustness and safety of 2d and 3d deep learning models against adversarial attacks
Benefiting from the rapid development of deep learning, 2D and 3D computer vision
applications are deployed in many safe-critical systems, such as autopilot and identity …
applications are deployed in many safe-critical systems, such as autopilot and identity …
Boosting adversarial transferability via gradient relevance attack
H Zhu, Y Ren, X Sui, L Yang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Plentiful adversarial attack researches have revealed the fragility of deep neural networks
(DNNs), where the imperceptible perturbations can cause drastic changes in the output …
(DNNs), where the imperceptible perturbations can cause drastic changes in the output …
Towards benchmarking and assessing visual naturalness of physical world adversarial attacks
Physical world adversarial attack is a highly practical and threatening attack, which fools real
world deep learning systems by generating conspicuous and maliciously crafted real world …
world deep learning systems by generating conspicuous and maliciously crafted real world …
Frequency-aware GAN for adversarial manipulation generation
Image manipulation techniques have drawn growing concerns as manipulated images
might cause morality and security problems. Various methods have been proposed to detect …
might cause morality and security problems. Various methods have been proposed to detect …
Unified physical-digital attack detection challenge
Abstract Face Anti-Spoofing (FAS) is crucial to safeguard Face Recognition (FR) Systems. In
real-world scenarios FRs are confronted with both physical and digital attacks. However …
real-world scenarios FRs are confronted with both physical and digital attacks. However …
Shift from texture-bias to shape-bias: Edge deformation-based augmentation for robust object recognition
Recent studies have shown the vulnerability of CNNs under perturbation noises, which is
partially caused by the reason that the well-trained CNNs are too biased toward the object …
partially caused by the reason that the well-trained CNNs are too biased toward the object …
Visual embedding augmentation in fourier domain for deep metric learning
Z Wang, Z Gao, G Wang, Y Yang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Deep Metric Learning (DML) is very effective for many computer vision applications such as
image retrieval or cross-modal matching. The common paradigm for DML is to seek metric …
image retrieval or cross-modal matching. The common paradigm for DML is to seek metric …
Adversarial attacks and defenses for semantic communication in vehicular metaverses
For vehicular Metaverses, one of the ultimate user-centric goals is to optimize the immersive
experience and Quality of Service (QoS) for users on board. Semantic Communication …
experience and Quality of Service (QoS) for users on board. Semantic Communication …
Unified physical-digital face attack detection
Face Recognition (FR) systems can suffer from physical (ie, print photo) and digital (ie,
DeepFake) attacks. However, previous related work rarely considers both situations at the …
DeepFake) attacks. However, previous related work rarely considers both situations at the …