國立虎尾科技大學 |

Privacy-Preserving Deep Learning = A Comprehensive Survey /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Privacy-Preserving Deep Learning/ by Kwangjo Kim, Harry Chandra Tanuwidjaja.
Reminder of title:	A Comprehensive Survey /
Author:	Kim, Kwangjo.
other author:	Tanuwidjaja, Harry Chandra.
Description:	XIV, 74 p. 21 illus., 14 illus. in color.online resource. :
Contained By:	Springer Nature eBook
Subject:	Computer security. -
Online resource:	https://doi.org/10.1007/978-981-16-3764-3
ISBN:	9789811637643

Privacy-Preserving Deep Learning = A Comprehensive Survey /
Kim, Kwangjo.

Privacy-Preserving Deep LearningA Comprehensive Survey /[electronic resource] :by Kwangjo Kim, Harry Chandra Tanuwidjaja. - 1st ed. 2021. - XIV, 74 p. 21 illus., 14 illus. in color.online resource. - SpringerBriefs on Cyber Security Systems and Networks,2522-557X. - SpringerBriefs on Cyber Security Systems and Networks,.

Introduction -- Definition and Classification -- Background Knowledge -- X-based Hybrid PPDL -- The Gap Between Theory and Application of X-based PPDL -- Federated Learning and Split Learning-based PPDL -- Analysis and Performance Comparison -- Attacks on DL and PPDL as the Possible Solutions -- Challenges and Future Work.

This book discusses the state-of-the-art in privacy-preserving deep learning (PPDL), especially as a tool for machine learning as a service (MLaaS), which serves as an enabling technology by combining classical privacy-preserving and cryptographic protocols with deep learning. Google and Microsoft announced a major investment in PPDL in early 2019. This was followed by Google’s infamous announcement of “Private Join and Compute,” an open source PPDL tools based on secure multi-party computation (secure MPC) and homomorphic encryption (HE) in June of that year. One of the challenging issues concerning PPDL is selecting its practical applicability despite the gap between the theory and practice. In order to solve this problem, it has recently been proposed that in addition to classical privacy-preserving methods (HE, secure MPC, differential privacy, secure enclaves), new federated or split learning for PPDL should also be applied. This concept involves building a cloud framework that enables collaborative learning while keeping training data on client devices. This successfully preserves privacy and while allowing the framework to be implemented in the real world. This book provides fundamental insights into privacy-preserving and deep learning, offering a comprehensive overview of the state-of-the-art in PPDL methods. It discusses practical issues, and leveraging federated or split-learning-based PPDL. Covering the fundamental theory of PPDL, the pros and cons of current PPDL methods, and addressing the gap between theory and practice in the most recent approaches, it is a valuable reference resource for a general audience, undergraduate and graduate students, as well as practitioners interested learning about PPDL from the scratch, and researchers wanting to explore PPDL for their applications.

ISBN: 9789811637643

Standard No.: 10.1007/978-981-16-3764-3doiSubjects--Topical Terms:

557122
Computer security.

LC Class. No.: QA76.9.A25

Dewey Class. No.: 005.8

Privacy-Preserving Deep Learning = A Comprehensive Survey /
LDR:03550nam a22003975i 4500 001 1050707
003 DE-He213
005 20210921232135.0
007 cr nn 008mamaa
008 220103s2021 si | s |||| 0|eng d
020 $a 9789811637643 $9 978-981-16-3764-3
024 7 $a 10.1007/978-981-16-3764-3 $2 doi
035 $a 978-981-16-3764-3
050 4 $a QA76.9.A25
072 7 $a URD $2 bicssc
072 7 $a COM060040 $2 bisacsh
072 7 $a URD $2 thema
082 0 4 $a 005.8 $2 23
100 1 $a Kim, Kwangjo. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1209190
245 1 0 $a Privacy-Preserving Deep Learning $h [electronic resource] : $b A Comprehensive Survey / $c by Kwangjo Kim, Harry Chandra Tanuwidjaja.
250 $a 1st ed. 2021.
264 1 $a Singapore : $b Springer Singapore : $b Imprint: Springer, $c 2021.
300 $a XIV, 74 p. 21 illus., 14 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a SpringerBriefs on Cyber Security Systems and Networks, $x 2522-557X
505 0 $a Introduction -- Definition and Classification -- Background Knowledge -- X-based Hybrid PPDL -- The Gap Between Theory and Application of X-based PPDL -- Federated Learning and Split Learning-based PPDL -- Analysis and Performance Comparison -- Attacks on DL and PPDL as the Possible Solutions -- Challenges and Future Work.
520 $a This book discusses the state-of-the-art in privacy-preserving deep learning (PPDL), especially as a tool for machine learning as a service (MLaaS), which serves as an enabling technology by combining classical privacy-preserving and cryptographic protocols with deep learning. Google and Microsoft announced a major investment in PPDL in early 2019. This was followed by Google’s infamous announcement of “Private Join and Compute,” an open source PPDL tools based on secure multi-party computation (secure MPC) and homomorphic encryption (HE) in June of that year. One of the challenging issues concerning PPDL is selecting its practical applicability despite the gap between the theory and practice. In order to solve this problem, it has recently been proposed that in addition to classical privacy-preserving methods (HE, secure MPC, differential privacy, secure enclaves), new federated or split learning for PPDL should also be applied. This concept involves building a cloud framework that enables collaborative learning while keeping training data on client devices. This successfully preserves privacy and while allowing the framework to be implemented in the real world. This book provides fundamental insights into privacy-preserving and deep learning, offering a comprehensive overview of the state-of-the-art in PPDL methods. It discusses practical issues, and leveraging federated or split-learning-based PPDL. Covering the fundamental theory of PPDL, the pros and cons of current PPDL methods, and addressing the gap between theory and practice in the most recent approaches, it is a valuable reference resource for a general audience, undergraduate and graduate students, as well as practitioners interested learning about PPDL from the scratch, and researchers wanting to explore PPDL for their applications.
650 0 $a Computer security. $3 557122
650 0 $a Machine learning. $3 561253
650 0 $a Artificial intelligence. $3 559380
650 0 $a Computer software. $3 528062
650 1 4 $a Privacy. $3 575491
650 2 4 $a Machine Learning. $3 1137723
650 2 4 $a Systems and Data Security. $3 677062
650 2 4 $a Artificial Intelligence. $3 646849
650 2 4 $a Professional Computing. $3 1115983
700 1 $a Tanuwidjaja, Harry Chandra. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1209192
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9789811637636
776 0 8 $i Printed edition: $z 9789811637650
830 0 $a SpringerBriefs on Cyber Security Systems and Networks, $x 2522-5561 $3 1280044
856 4 0 $u https://doi.org/10.1007/978-981-16-3764-3
912 $a ZDB-2-SCS
912 $a ZDB-2-SXCS
950 $a Computer Science (SpringerNature-11645)
950 $a Computer Science (R0) (SpringerNature-43710)