Diffusion models (DMs) have demonstrated advantageous potential on generative tasks.
Widespread interest exists in incorporating DMs into downstream applications, such as …

Federated learning (FL) is a technique that allows multiple participants to collaboratively
train a Deep Neural Network (DNN) without the need to centralize their data. Among other …

Abstract Protecting the Intellectual Property Rights (IPR) associated to Deep Neural
Networks (DNNs) is a pressing need pushed by the high costs required to train such …

We propose a watermarking method for protecting the Intellectual Property (IP) of Generative
Adversarial Networks (GANs). The aim is to watermark the GAN model so that any image …

Deep learning has been used to address various problems in a range of domains within
both academia and industry. However, the issue of intellectual property with deep learning …

Large pre-trained language models (PLMs) have proven to be a crucial component of
modern natural language processing systems. PLMs typically need to be fine-tuned on task …

Since training a deep neural network (DNN) is costly, the well-trained deep models can be
regarded as valuable intellectual property (IP) assets. The IP protection associated with …

The demand for methods to protect the Intellectual Property Rights (IPR) associated to Deep
Neural Networks (DNNs) is rising. Watermarking has been recently proposed as a way to …

Natural language generation (NLG) applications have gained great popularity due to the
powerful deep learning techniques and large training corpus. The deployed NLG models …

To trace the copyright of deep neural networks, an owner can embed its identity information
into its model as a watermark. The capacity of the watermark quantify the maximal volume of …