000 03741nam a22005655i 4500
001 978-981-19-6814-3
003 DE-He213
005 20240423125019.0
007 cr nn 008mamaa
008 230428s2023 si | s |||| 0|eng d
020 _a9789811968143
_9978-981-19-6814-3
024 7 _a10.1007/978-981-19-6814-3
_2doi
050 4 _aQ325.5-.7
072 7 _aUYQM
_2bicssc
072 7 _aMAT029000
_2bisacsh
072 7 _aUYQM
_2thema
082 0 4 _a006.31
_223
100 1 _aHuang, Xiaowei.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
245 1 0 _aMachine Learning Safety
_h[electronic resource] /
_cby Xiaowei Huang, Gaojie Jin, Wenjie Ruan.
250 _a1st ed. 2023.
264 1 _aSingapore :
_bSpringer Nature Singapore :
_bImprint: Springer,
_c2023.
300 _aXVII, 321 p. 1 illus.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aArtificial Intelligence: Foundations, Theory, and Algorithms,
_x2365-306X
505 0 _a1. 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 _aMachine 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 _aMachine learning.
650 0 _aData protection.
650 0 _aArtificial intelligence.
650 1 4 _aMachine Learning.
650 2 4 _aData and Information Security.
650 2 4 _aArtificial Intelligence.
700 1 _aJin, Gaojie.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
700 1 _aRuan, Wenjie.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9789811968136
776 0 8 _iPrinted edition:
_z9789811968150
776 0 8 _iPrinted edition:
_z9789811968167
830 0 _aArtificial Intelligence: Foundations, Theory, and Algorithms,
_x2365-306X
856 4 0 _uhttps://doi.org/10.1007/978-981-19-6814-3
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
942 _cSPRINGER
999 _c173242
_d173242