Results 31 to 40 of about 217,331 (267)

Target Training Does Adversarial Training Without Adversarial Samples

, 2021
arXiv admin note: text overlap with arXiv:2006 ...
openaire   +2 more sources

Prior-Guided Adversarial Initialization for Fast Adversarial Training

, 2022
Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robust accuracy against adversarial attacks suddenly and dramatically decreases.
Jia, Xiaojun, Zhang, Yong, Wei, Xingxing, Wu, Baoyuan, Ma, Ke, Wang, Jue, Cao, Xiaochun   +6 more
openaire   +2 more sources

Combining Adversaries with Anti-adversaries in Training

Proceedings of the AAAI Conference on Artificial Intelligence, 2023
Adversarial training is an effective learning technique to improve the robustness of deep neural networks. In this study, the influence of adversarial training on deep learning models in terms of fairness, robustness, and generalization is theoretically investigated under more general perturbation scope that different samples can have different ...
Zhou, Xiaoling, Yang, Nan, Wu, Ou
openaire   +2 more sources

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

Universal Adversarial Training

Proceedings of the AAAI Conference on Artificial Intelligence, 2020
Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad class of images, while still changing the predicted class label.
Shafahi, Ali, Najibi, Mahyar, Xu, Zheng, Dickerson, John, Davis, Larry S., Goldstein, Tom   +5 more
openaire   +3 more sources

CAT:Collaborative Adversarial Training

, 2023
Tech ...
Liu, Xingbin, Kuang, Huafeng, Lin, Xianming, Wu, Yongjian, Ji, Rongrong   +4 more
openaire   +2 more sources

EIFDAA: Evaluation of an IDS with function-discarding adversarial attacks in the IIoT

Heliyon, 2023
The complexity of the Industrial Internet of Things (IIoT) presents higher requirements for intrusion detection systems (IDSs). An adversarial attack is a threat to the security of machine learning-based IDSs.
Shiming Li, Jingxuan Wang, Yuhe Wang, Guohui Zhou, Yan Zhao   +4 more
doaj   +1 more source

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

Directional Adversarial Training for Robust Ownership-Based Recommendation System

IEEE Access, 2022
Machine learning algorithms are susceptible to cyberattacks, posing security problems in computer vision, speech recognition, and recommendation systems. So far, researchers have made great strides in adopting adversarial training as a defensive strategy.
Zhefu Wu, Agyemang Paul, Junzhuo Cao, Luping Fang   +3 more
doaj   +1 more source

MAT: A Multi-strength Adversarial Training Method to Mitigate Adversarial Attacks

, 2018
Some recent works revealed that deep neural networks (DNNs) are vulnerable to so-called adversarial attacks where input examples are intentionally perturbed to fool DNNs.
Chen, Yiran, Cheng, Hsin-Pai, Li, Hai, Li, Sicheng, Song, Chang, Wu, Chunpeng, Wu, Qing, Yang, Huanrui   +7 more
core   +1 more source