检索结果-南通市图书馆

One-Variable attack on the Industrial Fault Classification System and Its Defense

Engineering 2022年第12期19卷 240-251页

作者： Yue Zhuo Yuri A.W.Shardt Zhiqiang Ge State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Department of Automation Engineering Technische Universität IlmenauIlmenau D-98684Germany

Recently developed fault classification methods for industrial processes are mainly ***,models based on deep neural networks have significantly improved fault classification accuracy owing to the inclusion of a large number of data ***,these data-driven models are vulnerable to adversarial attacks;thus,small perturbations on the samples can cause the models to provide incorrect fault *** recent studies have demonstrated the vulnerability of machine learning methods and the existence of adversarial *** paper proposes a black-box attack method with an extreme constraint for a safe-critical industrial fault classification system:Only one variable can be perturbed to craft adversarial ***,to hide the adversarial samples in the visualization space,a Jacobian matrix is used to guide the perturbed variable selection,making the adversarial samples in the dimensional reduction space invisible to the human *** the one-variable attack(OVA)method,we explore the vulnerability of industrial variables and fault types,which can help understand the geometric characteristics of fault classification *** on the attack method,a corresponding adversarial training defense method is also proposed,which efficiently defends against an OVA and improves the prediction accuracy of the *** experiments,the proposed method was tested on two datasets from the Tennessee–Eastman process(TEP)and steel plates(SP).We explore the vulnerability and correlation within variables and faults and verify the effectiveness of OVAs and defenses for various classifiers and *** industrial fault classification systems,the attack success rate of our method is close to(on TEP)or even higher than(on SP)the current most effective first-order white-box attack method,which requires perturbation of all variables.

关键词： Adversarial samples black-box attack Industrial data security Fault classification system

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

Improving Transferability Reversible Adversarial Examples Based on Flipping Transformation

引用

国际计算机前沿大会会议论文集 2023年第1期 417-432页

作者： Youqing Fang Jingwen Jia Yuhai Yang Wanli Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China

Adding subtle perturbations to an image can cause the classiﬁcation model to misclassify,and such images are called adversarial ***-ial examples threaten the safe use of deep neural networks,but when combined with reversible data hiding(RDH)technology,they can protect images from being correctly identiﬁed by unauthorized models and recover the image lossless under authorized *** on this,the reversible adversarial example(RAE)is ***,existing RAE technology focuses on feasibility,attack success rate and image quality,but ignores transferability and time *** this paper,we optimize the data hiding structure and combine data augmentation technology,whichﬂips the input image in probability to avoid overﬁtting phenomenon on the *** the premise of maintaining a high success rate of white-box attacks and the image’s visual quality,the proposed method improves the transferability of reversible adversarial examples by approximately 16%and reduces the com-putational cost by approximately 43%compared to the state-of-the-art *** addition,the appropriateﬂip probability can be selected for different application scenarios.

关键词： reversible adversarial example black-box attack transferability complexity

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

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

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：