检索结果-南通市图书馆

Towards sustainable adversarial training with successive perturbation generation

Frontiers of Information Technology & Electronic Engineering 2024年第4期25卷 527-539页

作者： Wei LIN Lichuan LIAO College of Computer Science and Mathematics Fujian University of TechnologyFuzhou 350118China College of Economics and Management Xi’an University of TechnologyXi’an 710048China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou 350118China

Adversarial training with online-generated adversarial examples has achieved promising performance in defending adversarial attacks and improving robustness of convolutional neural network models.However,most existing adversarial training methods are dedicated to finding strong adversarial examples for forcing the model to learn the adversarial data distribution,which inevitably imposes a large computational overhead and results in a decrease in the generalization performance on clean data.In this paper,we show that progressively enhancing the adversarial strength of adversarial examples across training epochs can effectively improve the model robustness,and appropriate model shifting can preserve the generalization performance of models in conjunction with negligible computational cost.To this end,we propose a successive perturbation generation scheme for adversarial training(SPGAT),which progressively strengthens the adversarial examples by adding the perturbations on adversarial examples transferred from the previous epoch and shifts models across the epochs to improve the efficiency of adversarial training.The proposed SPGAT is both efficient and effective;e.g.,the computation time of our method is 900 min as against the 4100 min duration observed in the case of standard adversarial training,and the performance boost is more than 7%and 3%in terms of adversarial accuracy and clean accuracy,respectively.We extensively evaluate the SPGAT on various datasets,including small-scale MNIST,middle-scale CIFAR-10,and large-scale CIFAR-100.The experimental results show that our method is more efficient while performing favorably against state-of-the-art methods.

关键词： Adversarial training Adversarial attack stochastic weight average Machine learning Model generalization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：