Welcome to the Library Catalog of "Dunarea de Jos" University of Galati

Backdoor Attacks against Learning-Based Algorithms (Record no. 60245)

MARC details
000 -LEADER
fixed length control field 05150nam a22005895i 4500
001 - CONTROL NUMBER
control field 978-3-031-57389-7
003 - CONTROL NUMBER IDENTIFIER
control field DE-He213
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20251030112240.0
007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION
fixed length control field cr nn 008mamaa
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 240529s2024 sz | s |||| 0|eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
International Standard Book Number 9783031573897
-- 978-3-031-57389-7
024 7# - OTHER STANDARD IDENTIFIER
Standard number or code 10.1007/978-3-031-57389-7
Source of number or code doi
050 #4 - LIBRARY OF CONGRESS CALL NUMBER
Classification number TK5105.5-5105.9
072 #7 - SUBJECT CATEGORY CODE
Subject category code UKN
Source bicssc
072 #7 - SUBJECT CATEGORY CODE
Subject category code COM043000
Source bisacsh
072 #7 - SUBJECT CATEGORY CODE
Subject category code UKN
Source thema
100 1# - MAIN ENTRY--PERSONAL NAME
Personal name Li, Shaofeng.
Relator term author.
Relator code aut
-- http://id.loc.gov/vocabulary/relators/aut
9 (RLIN) 77712
245 10 - TITLE STATEMENT
Title Backdoor Attacks against Learning-Based Algorithms
Medium [electronic resource] /
Statement of responsibility, etc. by Shaofeng Li, Haojin Zhu, Wen Wu, Xuemin (Sherman) Shen.
250 ## - EDITION STATEMENT
Edition statement 1st ed. 2024.
264 #1 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE
Place of production, publication, distribution, manufacture Cham :
Name of producer, publisher, distributor, manufacturer Springer Nature Switzerland :
-- Imprint: Springer,
Date of production, publication, distribution, manufacture, or copyright notice 2024.
300 ## - PHYSICAL DESCRIPTION
Extent XI, 153 p. 58 illus., 56 illus. in color.
Other physical details online resource.
336 ## - CONTENT TYPE
Content type term text
Content type code txt
Source rdacontent
337 ## - MEDIA TYPE
Media type term computer
Media type code c
Source rdamedia
338 ## - CARRIER TYPE
Carrier type term online resource
Carrier type code cr
Source rdacarrier
347 ## - DIGITAL FILE CHARACTERISTICS
File type text file
Encoding format PDF
Source rda
490 1# - SERIES STATEMENT
Series statement Wireless Networks,
International Standard Serial Number 2366-1445
505 0# - FORMATTED CONTENTS NOTE
Formatted contents note Introduction -- Literature Review of Backdoor Attacks -- Invisible Backdoor Attacks in Image Classification Based Network Services -- Hidden Backdoor Attacks in NLP Based Network Services -- Backdoor Attacks and Defense in FL -- Summary and Future Directions.
520 ## - SUMMARY, ETC.
Summary, etc. This book introduces a new type of data poisoning attack, dubbed, backdoor attack. In backdoor attacks, an attacker can train the model with poisoned data to obtain a model that performs well on a normal input but behaves wrongly with crafted triggers. Backdoor attacks can occur in many scenarios where the training process is not entirely controlled, such as using third-party datasets, third-party platforms for training, or directly calling models provided by third parties. Due to the enormous threat that backdoor attacks pose to model supply chain security, they have received widespread attention from academia and industry. This book focuses on exploiting backdoor attacks in the three types of DNN applications, which are image classification, natural language processing, and federated learning. Based on the observation that DNN models are vulnerable to small perturbations, this book demonstrates that steganography and regularization can be adopted to enhance the invisibility of backdoor triggers. Based on image similarity measurement, this book presents two metrics to quantitatively measure the invisibility of backdoor triggers. The invisible trigger design scheme introduced in this book achieves a balance between the invisibility and the effectiveness of backdoor attacks. In the natural language processing domain, it is difficult to design and insert a general backdoor in a manner imperceptible to humans. Any corruption to the textual data (e.g., misspelled words or randomly inserted trigger words/sentences) must retain context-awareness and readability to human inspectors. This book introduces two novel hidden backdoor attacks, targeting three major natural language processing tasks, including toxic comment detection, neural machine translation, and question answering, depending on whether the targeted NLP platform accepts raw Unicode characters. The emerged distributed training framework, i.e., federated learning, has advantages in preserving users' privacy. It has been widely used in electronic medical applications, however, it also faced threats derived from backdoor attacks. This book presents a novel backdoor detection framework in FL-based e-Health systems. We hope this book can provide insightful lights on understanding the backdoor attacks in different types of learning-based algorithms, including computer vision, natural language processing, and federated learning. The systematic principle in this book also offers valuable guidance on the defense of backdoor attacks against future learning-based algorithms.
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element
9 (RLIN) 60157
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element
9 (RLIN) 65781
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element
9 (RLIN) 65782
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element
9 (RLIN) 55059
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element
9 (RLIN) 65689
650 24 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element
9 (RLIN) 65786
650 24 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element
9 (RLIN) 55059
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Zhu, Haojin.
Relator term author.
Relator code aut
-- http://id.loc.gov/vocabulary/relators/aut
9 (RLIN) 77713
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Wu, Wen.
Relator term author.
Relator code aut
-- http://id.loc.gov/vocabulary/relators/aut
9 (RLIN) 76575
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name Shen, Xuemin (Sherman).
Relator term author.
Relator code aut
-- http://id.loc.gov/vocabulary/relators/aut
9 (RLIN) 70857
710 2# - ADDED ENTRY--CORPORATE NAME
Corporate name or jurisdiction name as entry element SpringerLink (Online service)
773 0# - HOST ITEM ENTRY
Title Springer Nature eBook
776 08 - ADDITIONAL PHYSICAL FORM ENTRY
Relationship information Printed edition:
International Standard Book Number 9783031573880
776 08 - ADDITIONAL PHYSICAL FORM ENTRY
Relationship information Printed edition:
International Standard Book Number 9783031573903
776 08 - ADDITIONAL PHYSICAL FORM ENTRY
Relationship information Printed edition:
International Standard Book Number 9783031573910
830 #0 - SERIES ADDED ENTRY--UNIFORM TITLE
Uniform title Wireless Networks,
International Standard Serial Number 2366-1445
9 (RLIN) 67497
856 40 - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier <a href="https://doi.org/10.1007/978-3-031-57389-7">https://doi.org/10.1007/978-3-031-57389-7</a>
912 ## -
-- ZDB-2-SCS
912 ## -
-- ZDB-2-SXCS

No items available.

Biblioteca Universității "Dunărea de Jos" din Galați