Y Yu, CZ Xu - Proceedings of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Attackers can deceive neural networks by adding human imperceptive perturbations to their input data; this reveals the vulnerability and weak robustness of current deep-learning …
Classifiers trained using conventional empirical risk minimization or maximum likelihood methods are known to suffer dramatic performance degradations when tested over …
S Islam, I Alouani… - 2021 IEEE/ACM …, 2021 - ieeexplore.ieee.org
Deep neural networks (DNNs) are shown to be vulnerable to adversarial attacks—carefully crafted additive noise that undermines DNNs integrity. Previously proposed defenses …
Z He, AS Rakin, J Li… - Proceedings of the …, 2020 - openaccess.thecvf.com
Recently, a new paradigm of the adversarial attack on the quantized neural network weights has attracted great attention, namely, the Bit-Flip based adversarial weight attack, aka. Bit …
K Duncan, E Komendantskaya… - … Joint Conference on …, 2020 - ieeexplore.ieee.org
Neural networks are increasingly being moved to edge computing devices and smart sensors, to reduce latency and save bandwidth. Neural network compression such as …
S Wang, X Wang, S Ye, P Zhao… - 2018 IEEE Global …, 2018 - ieeexplore.ieee.org
Deep neural networks (DNNs) have been shown to be powerful models and perform extremely well on many complicated artificial intelligent tasks. However, recent research …
P Panda - Proceedings of the ACM/IEEE International Symposium …, 2020 - dl.acm.org
Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial attacks, wherein, a model gets fooled by applying slight perturbations on the input. In this paper, we …
J Guo, C Liu - Computer Vision–ECCV 2020: 16th European …, 2020 - Springer
Data poisoning attacks on machine learning models have attracted much recent attention, wherein poisoning samples are injected at the training phase to achieve adversarial goals at …
H Zhu, H Zheng, Y Zhu, X Sui - Information Sciences, 2023 - Elsevier
Deep neural networks are highly susceptible to imperceptible noise, even to the human eye. While high attack success rate has been achieved in white-box setting, the attack …