LEADER 03820nam 22006615 450 001 9910847583403321 005 20240404125717.0 010 $a981-9706-88-2 024 7 $a10.1007/978-981-97-0688-4 035 $a(CKB)31367761900041 035 $a(MiAaPQ)EBC31267082 035 $a(Au-PeEL)EBL31267082 035 $a(MiAaPQ)EBC31251670 035 $a(Au-PeEL)EBL31251670 035 $a(DE-He213)978-981-97-0688-4 035 $a(EXLCZ)9931367761900041 100 $a20240404d2024 u| 0 101 0 $aeng 135 $aur||||||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aRobust Machine Learning$b[electronic resource] $eDistributed Methods for Safe AI /$fby Rachid Guerraoui, Nirupam Gupta, Rafael Pinot 205 $a1st ed. 2024. 210 1$aSingapore :$cSpringer Nature Singapore :$cImprint: Springer,$d2024. 215 $a1 online resource (0 pages) 225 1 $aMachine Learning: Foundations, Methodologies, and Applications,$x2730-9916 311 $a981-9706-87-4 327 $aChapter 1. Context & Motivation -- Chapter 2. Basics of Machine Learning -- Chapter 3. Federated Machine Learning -- Chapter 4. Fundamentals of Robust Machine Learning -- Chapter 5. Optimal Robustness -- Chapter 6. Practical Robustness. . 330 $aToday, machine learning algorithms are often distributed across multiple machines to leverage more computing power and more data. However, the use of a distributed framework entails a variety of security threats. In particular, some of the machines may misbehave and jeopardize the learning procedure. This could, for example, result from hardware and software bugs, data poisoning or a malicious player controlling a subset of the machines. This book explains in simple terms what it means for a distributed machine learning scheme to be robust to these threats, and how to build provably robust machine learning algorithms. Studying the robustness of machine learning algorithms is a necessity given the ubiquity of these algorithms in both the private and public sectors. Accordingly, over the past few years, we have witnessed a rapid growth in the number of articles published on the robustness of distributed machine learning algorithms. We believe it is time to provide a clear foundation to this emerging and dynamic field. By gathering the existing knowledge and democratizing the concept of robustness, the book provides the basis for a new generation of reliable and safe machine learning schemes. In addition to introducing the problem of robustness in modern machine learning algorithms, the book will equip readers with essential skills for designing distributed learning algorithms with enhanced robustness. Moreover, the book provides a foundation for future research in this area. . 410 0$aMachine Learning: Foundations, Methodologies, and Applications,$x2730-9916 606 $aMachine learning 606 $aComputer security 606 $aMultiagent systems 606 $aCloud Computing 606 $aMachine Learning 606 $aPrinciples and Models of Security 606 $aMultiagent Systems 606 $aCloud Computing 615 0$aMachine learning. 615 0$aComputer security. 615 0$aMultiagent systems. 615 0$aCloud Computing. 615 14$aMachine Learning. 615 24$aPrinciples and Models of Security. 615 24$aMultiagent Systems. 615 24$aCloud Computing. 676 $a006.31 700 $aGuerraoui$b Rachid$01311091 701 $aGupta$b Nirupam$01736314 701 $aPinot$b Rafael$01736315 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910847583403321 996 $aRobust Machine Learning$94156170 997 $aUNINA