Related papers: Beyond Dataset Watermarking: Model-Level Copyright…

Recent progress in large language models enables the creation of realistic machine-generated content. Watermarking is a promising approach to distinguish machine-generated text from human text, embedding statistical signals in the output…

Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This…

Protecting intellectual property (IP) of text such as articles and code is increasingly important, especially as sophisticated attacks become possible, such as paraphrasing by large language models (LLMs) or even unauthorized training of…

Watermarking is a technique for hiding of data in a medium coverage so that its presence is not detectable by a human eye and is recoverable only by the authorized recipient. Two of the most important features of watermarked image are…

The task of discerning between generated and natural texts is increasingly challenging. In this context, watermarking emerges as a promising technique for ascribing generated text to a specific model. It alters the sampling generation…

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…

Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on these LLMs, which can benefit various natural language…

Deep neural networks are playing an important role in many real-life applications. After being trained with abundant data and computing resources, a deep neural network model providing service is endowed with economic value. An important…

Watermarking is an important copyright protection technology which generally embeds the identity information into the carrier imperceptibly. Then the identity can be extracted to prove the copyright from the watermarked carrier even after…

Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However,…

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately detect LLM-generated…

The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring…

Neural Radiance Fields (NeRF) have been gaining attention as a significant form of 3D content representation. With the proliferation of NeRF-based creations, the need for copyright protection has emerged as a critical issue. Although some…

Watermarking inserts invisible data into content to protect copyright. The embedded information provides proof of authorship and facilitates tracking illegal distribution, etc. Current robust watermarking techniques have been proposed to…

With the rapid advancement of speech generative models, unauthorized voice cloning poses significant privacy and security risks. Speech watermarking offers a viable solution for tracing sources and preventing misuse. Current watermarking…

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…

Text watermarking schemes have gained considerable attention in recent years, yet still face critical challenges in achieving simultaneous robustness, generalizability, and imperceptibility. This paper introduces a new embedding…

Large-scale vision-language models, especially CLIP, have demonstrated remarkable performance across diverse downstream tasks. Soft prompts, as carefully crafted modules that efficiently adapt vision-language models to specific tasks,…

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

Natural language processing (NLP) technology has shown great commercial value in applications such as sentiment analysis. But NLP models are vulnerable to the threat of pirated redistribution, damaging the economic interests of model…