Digital Watermarking for Machine Learning Model
Techniques, Protocols and Applications
- Publisher's listprice EUR 171.19
-
71 001 Ft (67 620 Ft + 5% VAT)
The price is estimated because at the time of ordering we do not know what conversion rates will apply to HUF / product currency when the book arrives. In case HUF is weaker, the price increases slightly, in case HUF is stronger, the price goes lower slightly.
- Discount 20% (cc. 14 200 Ft off)
- Discounted price 56 801 Ft (54 096 Ft + 5% VAT)
Subcribe now and take benefit of a favourable price.
Subscribe
71 001 Ft
Availability
printed on demand
Why don't you give exact delivery time?
Delivery time is estimated on our previous experiences. We give estimations only, because we order from outside Hungary, and the delivery time mainly depends on how quickly the publisher supplies the book. Faster or slower deliveries both happen, but we do our best to supply as quickly as possible.
Product details:
- Edition number 2023
- Publisher Springer Nature Singapore
- Date of Publication 31 May 2024
- Number of Volumes 1 pieces, Book
- ISBN 9789811975561
- Binding Paperback
- See also 9789811975530
- No. of pages225 pages
- Size 235x155 mm
- Language English
- Illustrations XVI, 225 p. 1 illus. Illustrations, black & white 558
Categories
Long description:
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.
More
Table of Contents:
Part I. Preliminary.- Chapter 1. Introduction.- Chapter 2. Ownership Verification Protocols for Deep Neural Network Watermarks.- Part II Techniques.- Chapter 3. ModelWatermarking for Image Recovery DNNs.- Chapter 4. The Robust and Harmless ModelWatermarking.- Chapter 5. Protecting Intellectual Property of Machine Learning Models via Fingerprinting the Classification Boundary.- Chapter 6. Protecting Image Processing Networks via Model Water.- Chapter 7. Watermarks for Deep Reinforcement Learning.- Chapter 8. Ownership Protection for Image Captioning Models.- Chapter 9.Protecting Recurrent Neural Network by Embedding Key.- Part III Applications.- Chapter 10. FedIPR: Ownership Verification for Federated Deep Neural Network Models.- Chapter 11. Model Auditing For Data Intellectual Property
More
