000			03810nam a22004215i 4500
999			_c361421 _d361421 _x1
001			361421
003			ES-MaUEC
005			20230102121356.0
006			a||||fo|||| 00| 0
007			cr nn nnnaamaa
008			210722s2021 si | s |||| 0|eng d
020			_a9789811637643
024	7		_a10.1007/978-981-16-3764-3 _2doi
040			_aES-MaUEC _bspa _cES-MaUEC _dES-MaUEC
050		4	_aQA76.9 .A25 _b2021 EB
100	1		_aKim, Kwangjo _eautor _9681115
245	1	0	_aPrivacy-Preserving Deep Learning : _bA Comprehensive Survey _cby Kwangjo Kim, Harry Chandra Tanuwidjaja
250			_aFirst edition 2021
264		1	_aSingapore _bSpringer International Publising _c2021
300			_a1 recurso en línea (XIV, 74 páginas) _b21 ilustraciones, 14 ilustraciones a color
336			_2rdacontent _aTexto _btxt
337			_2rdamedia _aelectrónico _bc
338			_2rdacarrier _arecurso electrónico _bcr
347			_aarchivo de texto _bPDF
490	0		_aSpringerBriefs on Cyber Security Systems and Networks _x2522-557X
490	0		_aComputer Science (SpringerNature-11645)
490	0		_aComputer Science (R0) (SpringerNature-43710)
505	0		_aIntroduction -- 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	3		_aThis 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.
988			_aSpringer_Computer_2021
650		7	_2embne _aSeguridad informática _9158200
700	1		_aTanuwidjaja, Harry Chandra _eautor
776	0	8	_iPrinted edition: _z9789811637636
776	0	8	_iPrinted edition: _z9789811637650
856	4	0	_uhttps://go.openathens.net/redirector/universidadeuropea.es?url=https://doi.org/10.1007/978-981-16-3764-3 _zAcceso a este recurso digital (usuarios Universidad Europea de Madrid)
942			_2lcc _cLE
998			_b01/2022 _dz _eu _zSI