A recipe for watermarking diffusion models
Diffusion models (DMs) have demonstrated advantageous potential on generative tasks.
Widespread interest exists in incorporating DMs into downstream applications, such as …
Widespread interest exists in incorporating DMs into downstream applications, such as …
When federated learning meets watermarking: A comprehensive overview of techniques for intellectual property protection
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 …
train a Deep Neural Network (DNN) without the need to centralize their data. Among other …
A survey of deep neural network watermarking techniques
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 …
Networks (DNNs) is a pressing need pushed by the high costs required to train such …
Supervised gan watermarking for intellectual property protection
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 …
Adversarial Networks (GANs). The aim is to watermark the GAN model so that any image …
When deep learning meets watermarking: A survey of application, attacks and defenses
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 …
both academia and industry. However, the issue of intellectual property with deep learning …
Watermarking pre-trained language models with backdooring
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 …
modern natural language processing systems. PLMs typically need to be fine-tuned on task …
Effective ambiguity attack against passport-based dnn intellectual property protection schemes through fully connected layer substitution
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 …
regarded as valuable intellectual property (IP) assets. The IP protection associated with …
DNN watermarking: Four challenges and a funeral
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 …
Neural Networks (DNNs) is rising. Watermarking has been recently proposed as a way to …
Protecting your nlg models with semantic and robust watermarks
Natural language generation (NLG) applications have gained great popularity due to the
powerful deep learning techniques and large training corpus. The deployed NLG models …
powerful deep learning techniques and large training corpus. The deployed NLG models …
Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
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 …
into its model as a watermark. The capacity of the watermark quantify the maximal volume of …