中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共3条，第1-3条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
Towards a unified framework for imperceptible textual attacks 期刊论文
APPLIED INTELLIGENCE, 2024, 页码: 14
作者:  Shi, Jiahui;  Li, Linjing;  Zeng, Daniel
收藏  |  浏览/下载：37/0  |  提交时间：2024/03/26
Adversarial attack  Backdoor attack  Natural language processing  Adversarial machine learning  
ASCL: Adversarial supervised contrastive learning for defense against word substitution attacks 期刊论文
NEUROCOMPUTING, 2022, 卷号: 510, 页码: 59-68
作者:  Shi, Jiahui;  Li, Linjing;  Zeng, Daniel
Adobe PDF(1054Kb)  |  收藏  |  浏览/下载：226/26  |  提交时间：2022/11/14
Adversarial example  Adversarial training  Model robustness  Contrastive learning  Natural language processing  
Perturbation Inactivation Based Adversarial Defense for Face Recognition 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 卷号: 17, 页码: 2947-2962
作者:  Ren, Min;  Zhu, Yuhao;  Wang, Yunlong;  Sun, Zhenan
Adobe PDF(5658Kb)  |  收藏  |  浏览/下载：255/49  |  提交时间：2022/11/14
Face recognition  Perturbation methods  Robustness  Immune system  Principal component analysis  Deep learning  Training  Adversarial machine learning  deep learning  graph neural network  face recognition