MARC details
000 -LEADER |
fixed length control field |
02629nam a2200361Ia 4500 |
000 - LEADER |
fixed length control field |
03824nam a22003975i 4500 |
001 - CONTROL NUMBER |
control field |
978-981-19-7554-7 |
003 - CONTROL NUMBER IDENTIFIER |
control field |
DE-He213 |
005 - DATE AND TIME OF LATEST TRANSACTION |
control field |
20240319120915.0 |
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 |
230529s2023 si | s |||| 0|eng d |
020 ## - INTERNATIONAL STANDARD BOOK NUMBER |
International Standard Book Number |
9789811975547 |
-- |
978-981-19-7554-7 |
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
Classification number |
6.31 |
245 ## - TITLE STATEMENT |
Title |
Digital Watermarking for Machine Learning Model |
Statement of responsibility, etc. |
edited by Lixin Fan, Chee Seng Chan, Qiang Yang. |
Medium |
[electronic resource] : |
250 ## - EDITION STATEMENT |
Edition statement |
1st ed. 2023. |
260 ## - PUBLICATION, DISTRIBUTION, ETC. |
Place of publication, distribution, etc. |
Singapore |
Name of publisher, distributor, etc. |
Springer Nature Singapore |
Date of publication, distribution, etc. |
2023 |
300 ## - PHYSICAL DESCRIPTION |
Extent |
XVI, 225 p. 1 illus. |
Other physical details |
online resource. |
520 ## - SUMMARY, ETC. |
Summary, etc. |
Machine learning (ML) models, especially large pretrained deep learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR). Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model's owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, natural language processing and reinforcement learning. This book covers the motivations, fundamentals, techniques and protocols for protecting ML models using watermarking. Furthermore, it showcases cutting-edge work in e.g. model watermarking, signature and passport embedding and their use cases in distributed federated learning settings. |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
Topical term or geographic name entry element |
Computer Imaging, Vision, Pattern Recognition and Graphics. |
9 (RLIN) |
32217 |
|
Topical term or geographic name entry element |
Computer vision. |
9 (RLIN) |
32218 |
|
Topical term or geographic name entry element |
Data and Information Security. |
9 (RLIN) |
32219 |
|
Topical term or geographic name entry element |
Data protection. |
9 (RLIN) |
32220 |
|
Topical term or geographic name entry element |
Image processing |
9 (RLIN) |
32221 |
|
Topical term or geographic name entry element |
Image processing. |
9 (RLIN) |
32221 |
|
Topical term or geographic name entry element |
Image Processing. |
9 (RLIN) |
32222 |
|
Topical term or geographic name entry element |
Machine learning. |
9 (RLIN) |
32223 |
|
Topical term or geographic name entry element |
Machine Learning. |
9 (RLIN) |
32224 |
700 ## - ADDED ENTRY--PERSONAL NAME |
Personal name |
Chan, Chee Seng. |
9 (RLIN) |
32225 |
|
Personal name |
Fan, Lixin. |
9 (RLIN) |
32226 |
|
Personal name |
Yang, Qiang. |
9 (RLIN) |
32227 |
856 ## - ELECTRONIC LOCATION AND ACCESS |
Uniform Resource Identifier |
<a href="https://doi.org/10.1007/978-981-19-7554-7">https://doi.org/10.1007/978-981-19-7554-7</a> |
942 ## - ADDED ENTRY ELEMENTS (KOHA) |
Koha item type |
e-Book |
Source of classification or shelving scheme |
Dewey Decimal Classification |