Related papers: Characterizing Watermark Numbers encoded as Reduci…
Recent advances in digital watermarking make use of deep neural networks for message embedding and extraction. They typically follow the ``encoder-noise layer-decoder''-based architecture. By deliberately establishing a differentiable noise…
Tree-Ring Watermarking is a significant technique for authenticating AI-generated images. However, its effectiveness in rectified flow-based models remains unexplored, particularly given the inherent challenges of these models with noise…
Digital image watermarking has been widely used in different applications such as copyright protection of digital media, such as audio, image, and video files. Two opposing criteria of robustness and transparency are the goals of…
With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope…
Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its reliability has been…
Software watermarking allows for embedding a mark into a piece of code, such that any attempt to remove the mark will render the code useless. Provably secure watermarking schemes currently seems limited to programs computing various…
Motivated by the problem of detecting AI-generated text, we consider the problem of watermarking the output of language models with provable guarantees. We aim for watermarks which satisfy: (a) undetectability, a cryptographic notion…
Watermarking has become one of promising techniques to not only aid in identifying AI-generated images but also serve as a deterrent against the unethical use of these models. However, the robustness of watermarking techniques has not been…
Graph-structured datasets are increasingly central to sensitive applications spanning social networks, biomedical research, and cryptographic systems. As organizations share these datasets with trusted parties for collaborative analysis,…
The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and public policy, raising growing concerns about data provenance and misuse. Watermarking offers a…
Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bit watermarking systems lack the capacity for large-scale…
Electronic counterfeiting is a longstanding problem with adverse long-term effects for many sectors, remaining on the rise. This article presents a novel low-cost technique to embed watermarking in devices with resistive-RAM (ReRAM) by…
Artificial Intelligence (AI) has found wide application, but also poses risks due to unintentional or malicious tampering during deployment. Regular checks are therefore necessary to detect and prevent such risks. Fragile watermarking is a…
Watermarking data for source tracking applications by its owner can be unfair for recipients because the data owner may redistribute the same watermarked data to many users. Hence, each data recipient should know the watermark embedded in…
Language models now routinely produce text that is difficult to distinguish from human writing, raising the need for robust tools to verify content provenance. Watermarking has emerged as a promising countermeasure, with existing work…
Pretraining on Graph Neural Networks (GNNs) has shown great power in facilitating various downstream tasks. As pretraining generally requires huge amount of data and computational resources, the pretrained GNNs are high-value Intellectual…
Speech watermarking techniques can proactively mitigate the potential harmful consequences of instant voice cloning techniques. These techniques involve the insertion of signals into speech that are imperceptible to humans but can be…
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 generated by the GAN contains an invisible watermark…
Internet is one of the most valuable resources for information communication and retrievals. Most multimedia signals today are in digital formats. The digital data can be duplicated and edited with great ease which has led to a need for…
Many image watermarking schemes have been proposed in recent years, but they usually involve embedding a watermark to the entire image without considering only a particular object in the image, which the image owner may be interested in.…