Results 11 to 20 of about 353,439 (278)
Adversarial symmetric GANs: Bridging adversarial samples and adversarial networks [PDF]
Neural Networks, 2021 Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability. Despite many training strategies proposed to improve training stability, this issue remains as a challenge. In this paper, we investigate the training instability from the perspective of adversarial samples and reveal that ...
Faqiang Liu +5 more
openaire +3 more sources
Combating Adversaries with Anti-adversaries
Proceedings of the AAAI Conference on Artificial Intelligence, 2022 Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we propose the anti-adversary layer, aimed at countering this effect.
Alfarra, M +5 more
openaire +2 more sources
IEEE Transactions on Cybernetics, 2022 16pages,9 figures ...
Chenghui Shi +6 more
openaire +3 more sources
Neural Networks, 2023 Adversarial robustness is considered as a required property of deep neural networks. In this study, we discover that adversarially trained models might have significantly different characteristics in terms of margin and smoothness, even they show similar robustness.
Hoki Kim +3 more
openaire +3 more sources
Efficient Adversarial Training With Transferable Adversarial Examples [PDF]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost of generating strong adversarial examples during training.
Zheng, Haizhong +4 more
openaire +2 more sources
Denoising Adversarial Autoencoders [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2019 Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space.
Antonia Creswell, Anil Anthony Bharath
openaire +5 more sources
Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019 Perceptual ad-blocking is a novel approach that detects online advertisements based on their visual content. Compared to traditional filter lists, the use of perceptual signals is believed to be less prone to an arms race with web publishers and ad networks. We demonstrate that this may not be the case.
Tramèr, Florian +4 more
openaire +2 more sources
Probabilistic Categorical Adversarial Attack & Adversarial Training
, 2022 The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of extensive exploration.
Xu, Han +6 more
openaire +2 more sources
SSRN Electronic Journal, 2022 Adversarial samples have drawn a lot of attention from the Machine Learning community in the past few years. An adverse sample is an artificial data point coming from an imperceptible modification of a sample point aiming at misleading. Surprisingly, in financial research, little has been done in relation to this topic from a concrete trading point of ...
openaire +2 more sources
Boosting Fast Adversarial Training With Learnable Adversarial Initialization
IEEE Transactions on Image Processing, 2022 Accepted by ...
Xiaojun Jia +4 more
openaire +3 more sources