Related papers: ClearMark: Intuitive and Robust Model Watermarking…

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

The design of an effective multi-bit watermarking algorithm hinges upon finding a good trade-off between the three fundamental requirements forming the watermarking trade-off triangle, namely, robustness against network modifications,…

Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe risks of unauthorized use. Although digital watermarking…

Many learning tasks require us to deal with graph data which contains rich relational information among elements, leading increasing graph neural network (GNN) models to be deployed in industrial products for improving the quality of…

Being trained on large and vast datasets, visual foundation models (VFMs) can be fine-tuned for diverse downstream tasks, achieving remarkable performance and efficiency in various computer vision applications. The high computation cost of…

The rapid advancement of deep neural networks (DNNs) heavily relies on large-scale, high-quality datasets. However, unauthorized commercial use of these datasets severely violates the intellectual property rights of dataset owners. Existing…

Robust invisible watermarking aims to embed hidden information into images such that the watermark can survive various image manipulations. However, the rise of powerful diffusion-based image generation and editing techniques poses a new…

Watermarking deep neural network (DNN) models has attracted a great deal of attention and interest in recent years because of the increasing demand to protect the intellectual property of DNN models. Many practical algorithms have been…

Convolutional Neural Networks (CNNs) deployed in real-life applications such as autonomous vehicles have shown to be vulnerable to manipulation attacks, such as poisoning attacks and fine-tuning. Hence, it is essential to ensure the…

The huge supporting training data on the Internet has been a key factor in the success of deep learning models. However, this abundance of public-available data also raises concerns about the unauthorized exploitation of datasets for…

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance. Watermarking addresses this issue by embedding a unique identifier into the model, while preserving its performance. However,…

Being trained on large and diverse datasets, visual foundation models (VFMs) can be fine-tuned to achieve remarkable performance and efficiency in various downstream computer vision tasks. The high computational cost of data collection and…

Static deep neural network (DNN) watermarking techniques typically employ irreversible methods to embed watermarks into the DNN model weights. However, this approach causes permanent damage to the watermarked model and fails to meet the…

Watermarking embeds information into digital content like images, audio, or text, imperceptible to humans but robustly detectable by specific algorithms. This technology has important applications in many challenges of the industry such as…

The prosperity of deep neural networks (DNNs) is largely benefited from open-source datasets, based on which users can evaluate and improve their methods. In this paper, we revisit backdoor-based dataset ownership verification (DOV), which…

The last decade of machine learning has seen drastic increases in scale and capabilities. Deep neural networks (DNNs) are increasingly being deployed in the real world. However, they are difficult to analyze, raising concerns about using…

Embedding watermarks into the output of generative models is essential for establishing copyright and verifiable ownership over the generated content. Emerging diffusion model watermarking methods either embed watermarks in the frequency…

Imperceptible digital watermarking is important in copyright protection, misinformation prevention, and responsible generative AI. We propose TrustMark - a GAN-based watermarking method with novel design in architecture and spatio-spectra…