000			03423nam a22003617a 4500
003			CSPC
005			20260708143535.0
008			260708s2023 si a b 000 0 eng d
020			_a9789811968136
040			_aCSPC _beng _cCSPC _dCSPC _erda
050		4	_aQ325.5 _b.H83 2023
082	0	4	_a006.31 _bH860m _223
100	1		_aHuang, Xiaowei, _eauthor.
245	1	0	_aMachine learning safety / _cXiaowei Huang, Gaojie Jin, and Wenjie Ruan.
264		1	_aSingapore : _bSpringer Nature Singapore Pte Ltd., _c2023.
300			_axvii, 321 pages : _billustrations ; _c24 cm.
336			_2rdacontent _atext
337			_2rdamedia _aunmediated
338			_2rdacarrier _avolume
490	0		_aArtificial intelligence : foundations, theory, and algorithms
504			_aIncludes bibliographical references.
505	0		_aSafety properties -- Machine learning basics -- Model evaluation methods -- Safety and security properties -- Practice -- Safety threats -- Decision tree -- K-nearest neighbor -- Linear regression -- Naive bayes -- Loss function and gradient descent -- Deep learning -- Safety solutions -- Verification of deep learning -- Enhancement to safety and security of deep learning -- Extended safety solutions -- Deep reinforced learning -- Testing techniques -- Reliability assessment -- Assurance of machine learning lifecycle -- Probabilistic graph models for feature robustness -- Appendix: mathematical foundations and competition -- probability theory -- Linear algebra -- Probabilistic graph models -- Competition: resilience to adversarial attack.
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"-- Worldcat.
650		0	_aMachine learning.
650		0	_aData protection.
650		0	_aArtificial intelligence.
650		0	_aMachine learning _xSafety measures.
650		0	_aComputer security.
700	1		_aJin, Gaojie, _eauthor.
700	1		_aRuan, Wenjie, _eauthor.
942			_2ddc _n0 _cBK _h006.31 _iH860m _kGRD _m2023 _e23
999			_c32564 _d32564