Kategoria BISAC: Computers >> Image Processing

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...

The 10 full papers presented at PIPPI 2023 were carefully reviewed and selected from 14 submissions. PIPPI 2023 workshop complements the main MICCAI conference by providing a focused discussion on the challenges of image analysis techniques as applied to the fetal and infant...

This book constitutes the refereed proceedings of the 12th International Conference on Artificial Intelligence and Mobile Services, AIMS 2023, Held as Part of the Services Conference Federation, SCF 2023, Honolulu, HI, USA, September 23–26, 2023.

The 9 full papers presented together and selected from 16 submissions. The conference focuses on AI modeling; AI analysis; AI & mobile applications; AI architecture; AI management; AI engineering; mobile backend as a service (MBaaS); and user experience of AI & mobile services.