國立虎尾科技大學 |

Federated learning = a primer for mathematicians /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Federated learning/ by Mei Kobayashi.
Reminder of title:	a primer for mathematicians /
Author:	Kobayashi, Mei.
Published:	Singapore :Springer Nature Singapore : : 2025.,
Description:	xiv, 82 p. :ill., digital ; : 24 cm.;
Contained By:	Springer Nature eBook
Subject:	Federated learning (Machine learning) -
Online resource:	https://doi.org/10.1007/978-981-96-9223-1
ISBN:	9789819692231

Federated learning = a primer for mathematicians /
Kobayashi, Mei.

Federated learninga primer for mathematicians /[electronic resource] :by Mei Kobayashi. - Singapore :Springer Nature Singapore :2025. - xiv, 82 p. :ill., digital ;24 cm. - ICIAM2023 Springer series,v. 43091-3101 ;. - ICIAM2023 Springer series ;v. 4..

Introduction -- Multiparty Computation -- Edge Computing -- Federated Learning -- Data Leakage and Data Poisoning.

This book serves as a primer on a secure computing framework known as federated learning. Federated learning is the study of methods to enable multiple parties to collaboratively train machine learning/AI models, while each party retains its own, raw data on-premise, never sharing it with others. This book is designed to be accessible to anyone with a background in undergraduate applied mathematics. It covers the basics of topics from computer science that are needed to understand examples of simple federated computing frameworks. It is my hope that by learning basic concepts and technical jargon from computer science, readers will be able to start collaborative work with researchers interested in secure computing. Chap. 1 provides the background and motivation for data security and federated learning and the simplest type of neural network. Chap. 2 introduces the idea of multiparty computation (MPC) and why enhancements are needed to provide security and privacy. Chap. 3 discusses edge computing, a distributed computing model in which data processing takes place on local devices, closer to where it is being generated. Advances in hardware and economies of scale have made it possible for edge computing devices to be embedded in everyday consumer products to process large volumes of data quickly and produce results in near real-time. Chap. 4 covers the basics of federated learning. Federated learning is a framework that enables multiple parties to collaboratively train AI models, while each party retains control of its own raw data, never sharing it with others. Chap. 5 discusses two attacks that target weaknesses of federated learning systems: (1) data leakage, i.e., inferring raw data used to train an AI model by unauthorized parties, and (2) data poisoning, i.e., a cyberattack that compromises data used to train an AI model to manipulate its output.

ISBN: 9789819692231

Standard No.: 10.1007/978-981-96-9223-1doiSubjects--Topical Terms:

1487729
Federated learning (Machine learning)

LC Class. No.: Q325.65

Dewey Class. No.: 006.31

Federated learning = a primer for mathematicians /
LDR:03028nam a2200337 a 4500 001 1166526
003 DE-He213
005 20250806165331.0
006 m d
007 cr nn 008maaau
008 251217s2025 si s 0 eng d
020 $a 9789819692231 $q (electronic bk.)
020 $a 9789819692224 $q (paper)
024 7 $a 10.1007/978-981-96-9223-1 $2 doi
035 $a 978-981-96-9223-1
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.65
072 7 $a UYA $2 bicssc
072 7 $a MAT003000 $2 bisacsh
072 7 $a UYA $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.65 $b .K75 2025
100 1 $a Kobayashi, Mei. $3 528231
245 1 0 $a Federated learning $h [electronic resource] : $b a primer for mathematicians / $c by Mei Kobayashi.
260 $a Singapore : $c 2025. $b Springer Nature Singapore : $b Imprint: Springer,
300 $a xiv, 82 p. : $b ill., digital ; $c 24 cm.
490 1 $a ICIAM2023 Springer series, $x 3091-3101 ; $v v. 4
505 0 $a Introduction -- Multiparty Computation -- Edge Computing -- Federated Learning -- Data Leakage and Data Poisoning.
520 $a This book serves as a primer on a secure computing framework known as federated learning. Federated learning is the study of methods to enable multiple parties to collaboratively train machine learning/AI models, while each party retains its own, raw data on-premise, never sharing it with others. This book is designed to be accessible to anyone with a background in undergraduate applied mathematics. It covers the basics of topics from computer science that are needed to understand examples of simple federated computing frameworks. It is my hope that by learning basic concepts and technical jargon from computer science, readers will be able to start collaborative work with researchers interested in secure computing. Chap. 1 provides the background and motivation for data security and federated learning and the simplest type of neural network. Chap. 2 introduces the idea of multiparty computation (MPC) and why enhancements are needed to provide security and privacy. Chap. 3 discusses edge computing, a distributed computing model in which data processing takes place on local devices, closer to where it is being generated. Advances in hardware and economies of scale have made it possible for edge computing devices to be embedded in everyday consumer products to process large volumes of data quickly and produce results in near real-time. Chap. 4 covers the basics of federated learning. Federated learning is a framework that enables multiple parties to collaboratively train AI models, while each party retains control of its own raw data, never sharing it with others. Chap. 5 discusses two attacks that target weaknesses of federated learning systems: (1) data leakage, i.e., inferring raw data used to train an AI model by unauthorized parties, and (2) data poisoning, i.e., a cyberattack that compromises data used to train an AI model to manipulate its output.
650 0 $a Federated learning (Machine learning) $3 1487729
650 1 4 $a Mathematical Applications in Computer Science. $3 815331
650 2 4 $a Mathematics of Computing. $3 669457
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
830 0 $a ICIAM2023 Springer series ; $v v. 4. $3 1495301
856 4 0 $u https://doi.org/10.1007/978-981-96-9223-1
950 $a Mathematics and Statistics (SpringerNature-11649)