Machine learning algorithms : adversarial robustness in signal processing / Fuwei Li, Lifeng Lai, Shuguang Cui.
2022
Q325.5
Linked e-resources
Linked Resource
Online Access
Concurrent users
Unlimited
Authorized users
Authorized users
Document Delivery Supplied
Can lend chapters, not whole ebooks
Details
Title
Machine learning algorithms : adversarial robustness in signal processing / Fuwei Li, Lifeng Lai, Shuguang Cui.
Author
Li, Fuwei.
ISBN
9783031163753 (electronic bk.)
3031163753 (electronic bk.)
3031163745
9783031163746
3031163753 (electronic bk.)
3031163745
9783031163746
Publication Details
Cham : Springer, 2022.
Language
English
Description
1 online resource (109 p.).
Item Number
10.1007/978-3-031-16375-3 doi
Call Number
Q325.5
Dewey Decimal Classification
006.3/1
Summary
This book demonstrates the optimal adversarial attacks against several important signal processing algorithms. Through presenting the optimal attacks in wireless sensor networks, array signal processing, principal component analysis, etc, the authors reveal the robustness of the signal processing algorithms against adversarial attacks. Since data quality is crucial in signal processing, the adversary that can poison the data will be a significant threat to signal processing. Therefore, it is necessary and urgent to investigate the behavior of machine learning algorithms in signal processing under adversarial attacks. The authors in this book mainly examine the adversarial robustness of three commonly used machine learning algorithms in signal processing respectively: linear regression, LASSO-based feature selection, and principal component analysis (PCA). As to linear regression, the authors derive the optimal poisoning data sample and the optimal feature modifications, and also demonstrate the effectiveness of the attack against a wireless distributed learning system. The authors further extend the linear regression to LASSO-based feature selection and study the best strategy to mislead the learning system to select the wrong features. The authors find the optimal attack strategy by solving a bi-level optimization problem and also illustrate how this attack influences array signal processing and weather data analysis. In the end, the authors consider the adversarial robustness of the subspace learning problem. The authors examine the optimal modification strategy under the energy constraints to delude the PCA-based subspace learning algorithm. This book targets researchers working in machine learning, electronic information, and information theory as well as advanced-level students studying these subjects. R&D engineers who are working in machine learning, adversarial machine learning, robust machine learning, and technical consultants working on the security and robustness of machine learning are likely to purchase this book as a reference guide.
Bibliography, etc. Note
Includes bibliographical references.
Access Note
Access limited to authorized users.
Source of Description
Online resource; title from PDF title page (SpringerLink, viewed November 29, 2022).
Added Author
Lai, Lifeng.
Cui, Shuguang.
Cui, Shuguang.
Series
Wireless networks (Springer (Firm))
Available in Other Form
Machine Learning Algorithms
Linked Resources
Online Access
Record Appears in
Online Resources > Ebooks
All Resources
All Resources
Table of Contents
Chapter. 1. Introduction
Chapter. 2. Optimal Feature Manipulation Attacks Against Linear Regression
Chapter. 3. On the Adversarial Robustness of LASSO Based Feature Selection
Chapter. 4. On the Adversarial Robustness of Subspace Learning
Chapter. 5. Summary and Extensions
Chapter. 6. Appendix.
Chapter. 2. Optimal Feature Manipulation Attacks Against Linear Regression
Chapter. 3. On the Adversarial Robustness of LASSO Based Feature Selection
Chapter. 4. On the Adversarial Robustness of Subspace Learning
Chapter. 5. Summary and Extensions
Chapter. 6. Appendix.