Results 41 to 50 of about 3,499,798 (281)

Gray-Box Adversarial Training [PDF]

, 2018
Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust models. In order to scale adversarial training for large datasets, these perturbations can only be crafted using fast
Vivek B. S., Konda Reddy Mopuri, R. Venkatesh Babu   +2 more
openaire   +3 more sources

Case-Aware Adversarial Training

CoRR, 2022
The neural network (NN) becomes one of the most heated type of models in various signal processing applications. However, NNs are extremely vulnerable to adversarial examples (AEs). To defend AEs, adversarial training (AT) is believed to be the most effective method while due to the intensive computation, AT is limited to be applied in most ...
Mingyuan Fan 0003, Yang Liu 0118, Wenzhong Guo, Ximeng Liu, Jianhua Li 0002   +4 more
openaire   +3 more sources

Defending Poisoning Attacks in Federated Learning via Adversarial Training Method

, 2020
Recently, federated learning has shown its significant advantages in protecting training data privacy by maintaining a joint model across multiple clients.
Chen, Bing, Di Wu, Liu, Chengyong, Chengyong Liu, Zhang, Jiale, Jiale Zhang, Bing Chen, Wu, Di   +7 more
core   +1 more source

Strength-Adaptive Adversarial Training [PDF]

, 2022
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network.
Liu, Tongliang, Shen, Li, Gong, Mingming, Wang, Nannan, Zhou, Dawei, Yu, Jun, Yu, Chaojian, Han, Bo   +7 more
core   +1 more source

Adversarial Training for Sketch Retrieval [PDF]

, 2016
Generative Adversarial Networks (GAN) are able to learn excellent representations for unlabelled data which can be applied to image generation and scene classification. Representations learned by GANs have not yet been applied to retrieval. In this paper, we show that the representations learned by GANs can indeed be used for retrieval.
Antonia Creswell, Anil Anthony Bharath
openaire   +3 more sources

A Sublinear Adversarial Training Algorithm

CoRR, 2022
Adversarial training is a widely used strategy for making neural networks resistant to adversarial perturbations. For a neural network of width $m$, $n$ input training data in $d$ dimension, it takes $Ω(mnd)$ time cost per training iteration for the forward and backward computation.
Yeqi Gao, Lianke Qin, Zhao Song 0002, Yitan Wang   +3 more
openaire   +4 more sources

Target Training Does Adversarial Training Without Adversarial Samples

CoRR, 2021
arXiv admin note: text overlap with arXiv:2006 ...
openaire   +3 more sources

Adversarial Training for Commonsense Inference [PDF]

Proceedings of the 5th Workshop on Representation Learning for NLP, 2020
6 pages, Accepted to ACL2020 RepL4NLP ...
Lis Pereira, Xiaodong Liu 0003, Fei Cheng 0002, Masayuki Asahara, Ichiro Kobayashi   +4 more
openaire   +3 more sources

Fast-M Adversarial Training Algorithm for Deep Neural Networks

Applied Sciences
Although deep neural networks have been successfully applied in many fields, research studies show that neural network models are easily disrupted by small malicious inputs, greatly reducing their performance.
Yu Ma, Dou An, Zhixiang Gu, Jie Lin, Weiyu Liu   +4 more
doaj   +1 more source

Deep Learning Based Robust Text Classification Method via Virtual Adversarial Training

IEEE Access, 2020
The existing methods of generating adversarial texts usually change the original meanings of texts significantly and even generate the unreadable texts.
Wei Zhang, Qian Chen, Yunfang Chen
doaj   +1 more source