Central Library

Backdoor Attacks against Learning-Based Algorithms (Record no. 88110)

000 -LEADER
fixed length control field 05129nam a22005895i 4500
001 - CONTROL NUMBER
control field 978-3-031-57389-7
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20240730172223.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 240529s2024 sz | s |||| 0|eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
ISBN 9783031573897
-- 978-3-031-57389-7
082 04 - CLASSIFICATION NUMBER
Call Number 004.6
100 1# - AUTHOR NAME
Author Li, Shaofeng.
245 10 - TITLE STATEMENT
Title Backdoor Attacks against Learning-Based Algorithms
250 ## - EDITION STATEMENT
Edition statement 1st ed. 2024.
300 ## - PHYSICAL DESCRIPTION
Number of Pages XI, 153 p. 58 illus., 56 illus. in color.
490 1# - SERIES STATEMENT
Series statement Wireless Networks,
505 0# - FORMATTED CONTENTS NOTE
Remark 2 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.
700 1# - AUTHOR 2
Author 2 Zhu, Haojin.
700 1# - AUTHOR 2
Author 2 Wu, Wen.
700 1# - AUTHOR 2
Author 2 Shen, Xuemin (Sherman).
856 40 - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier https://doi.org/10.1007/978-3-031-57389-7
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type eBooks
264 #1 -
-- Cham :
-- Springer Nature Switzerland :
-- Imprint: Springer,
-- 2024.
336 ## -
-- text
-- txt
-- rdacontent
337 ## -
-- computer
-- c
-- rdamedia
338 ## -
-- online resource
-- cr
-- rdacarrier
347 ## -
-- text file
-- PDF
-- rda
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Computer networks .
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Wireless communication systems.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Mobile communication systems.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Machine learning.
650 14 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Computer Communication Networks.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Wireless and Mobile Communication.
650 24 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Machine Learning.
830 #0 - SERIES ADDED ENTRY--UNIFORM TITLE
-- 2366-1445
912 ## -
-- ZDB-2-SCS
912 ## -
-- ZDB-2-SXCS

No items available.