國立高雄大學圖資館 |

Language: English

Back

Machine learning safety

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine learning safetyby Xiaowei Huang, Gaojie Jin, Wenjie Ruan.
Author:	Huang, Xiaowei.
other author:	Jin, Gaojie.
Published:	Singapore :Springer Nature Singapore :2023.
Description:	xvii, 321 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Machine learningSafety measures.
Online resource:	https://doi.org/10.1007/978-981-19-6814-3
ISBN:	9789811968143$q(electronic bk.)

Machine learning safety
Huang, Xiaowei.

Machine learning safety[electronic resource] /by Xiaowei Huang, Gaojie Jin, Wenjie Ruan. - Singapore :Springer Nature Singapore :2023. - xvii, 321 p. :ill., digital ;24 cm. - Artificial intelligence: foundations, theory, and algorithms,2365-306X. - Artificial intelligence: foundations, theory, and algorithms..

1. Introduction -- 2. Safety of Simple Machine Learning Models -- 3. Safety of Deep Learning -- 4. Robustness Verification of Deep Learning -- 5. Enhancement to Robustness and Generalization -- 6. Probabilistic Graph Model -- A. Mathematical Foundations -- B. Competitions.

Machine learning algorithms allow computers to learn without being explicitly programmed. Their application is now spreading to highly sophisticated tasks across multiple domains, such as medical diagnostics or fully autonomous vehicles. While this development holds great potential, it also raises new safety concerns, as machine learning has many specificities that make its behaviour prediction and assessment very different from that for explicitly programmed software systems. This book addresses the main safety concerns with regard to machine learning, including its susceptibility to environmental noise and adversarial attacks. Such vulnerabilities have become a major roadblock to the deployment of machine learning in safety-critical applications. The book presents up-to-date techniques for adversarial attacks, which are used to assess the vulnerabilities of machine learning models; formal verification, which is used to determine if a trained machine learning model is free of vulnerabilities; and adversarial training, which is used to enhance the training process and reduce vulnerabilities. The book aims to improve readers' awareness of the potential safety issues regarding machine learning models. In addition, it includes up-to-date techniques for dealing with these issues, equipping readers with not only technical knowledge but also hands-on practical skills.

ISBN: 9789811968143$q(electronic bk.)

Standard No.: 10.1007/978-981-19-6814-3doiSubjects--Topical Terms:

944129
Machine learning
--Safety measures.

LC Class. No.: Q325.5

Dewey Class. No.: 006.31

Machine learning safety
LDR:02707nmm a2200337 a 4500 001 642561
003 DE-He213
005 20230428133604.0
006 m d
007 cr nn 008maaau
008 231123s2023 si s 0 eng d
020 $a 9789811968143$q(electronic bk.)
020 $a 9789811968136$q(paper)
024 7 $a 10.1007/978-981-19-6814-3 $2 doi
035 $a 978-981-19-6814-3
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.5 $b .H874 2023
100 1 $a Huang, Xiaowei. $3 949904
245 1 0 $a Machine learning safety $h [electronic resource] / $c by Xiaowei Huang, Gaojie Jin, Wenjie Ruan.
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2023.
300 $a xvii, 321 p. : $b ill., digital ; $c 24 cm.
490 1 $a Artificial intelligence: foundations, theory, and algorithms, $x 2365-306X
505 0 $a 1. Introduction -- 2. Safety of Simple Machine Learning Models -- 3. Safety of Deep Learning -- 4. Robustness Verification of Deep Learning -- 5. Enhancement to Robustness and Generalization -- 6. Probabilistic Graph Model -- A. Mathematical Foundations -- B. Competitions.
520 $a Machine learning algorithms allow computers to learn without being explicitly programmed. Their application is now spreading to highly sophisticated tasks across multiple domains, such as medical diagnostics or fully autonomous vehicles. While this development holds great potential, it also raises new safety concerns, as machine learning has many specificities that make its behaviour prediction and assessment very different from that for explicitly programmed software systems. This book addresses the main safety concerns with regard to machine learning, including its susceptibility to environmental noise and adversarial attacks. Such vulnerabilities have become a major roadblock to the deployment of machine learning in safety-critical applications. The book presents up-to-date techniques for adversarial attacks, which are used to assess the vulnerabilities of machine learning models; formal verification, which is used to determine if a trained machine learning model is free of vulnerabilities; and adversarial training, which is used to enhance the training process and reduce vulnerabilities. The book aims to improve readers' awareness of the potential safety issues regarding machine learning models. In addition, it includes up-to-date techniques for dealing with these issues, equipping readers with not only technical knowledge but also hands-on practical skills.
650 0 $a Machine learning $x Safety measures. $3 944129
650 0 $a Computer security. $3 184416
650 1 4 $a Machine Learning. $3 833608
650 2 4 $a Data and Information Security. $3 913130
650 2 4 $a Artificial Intelligence. $3 212515
700 1 $a Jin, Gaojie. $3 949905
700 1 $a Ruan, Wenjie. $3 949906
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Artificial intelligence: foundations, theory, and algorithms. $3 729041
856 4 0 $u https://doi.org/10.1007/978-981-19-6814-3
950 $a Computer Science (SpringerNature-11645)