Digital Watermarking for Machine Learning Model
Digital Watermarking for Machine Learning Model [electronic resource] :
edited by Lixin Fan, Chee Seng Chan, Qiang Yang.
- 1st ed. 2023.
- Singapore Springer Nature Singapore 2023
- XVI, 225 p. 1 illus. online resource.
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.
9789811975547
Computer Imaging, Vision, Pattern Recognition and Graphics.
Computer vision.
Data and Information Security.
Data protection.
Image processing
Image processing.
Image Processing.
Machine learning.
Machine Learning.
6.31
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.
9789811975547
Computer Imaging, Vision, Pattern Recognition and Graphics.
Computer vision.
Data and Information Security.
Data protection.
Image processing
Image processing.
Image Processing.
Machine learning.
Machine Learning.
6.31