Related papers: Edit Distance Robust Watermarks via Indexing Pseud…
We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a language model more than once, as even benign users do. And…
The effectiveness of watermark algorithms in AI-generated text identification has garnered significant attention. Concurrently, an increasing number of watermark algorithms have been proposed to enhance the robustness against various…
Watermarks are an essential tool for identifying AI-generated content. Recently, Christ and Gunn (CRYPTO '24) introduced pseudorandom error-correcting codes (PRCs), which are equivalent to watermarks with strong robustness and quality…
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…
A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity and high detection overhead. In parallel, recent research has…
Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by…
Pseudorandom codes are error-correcting codes with the property that no efficient adversary can distinguish encodings from uniformly random strings. They were recently introduced by Christ and Gunn [CRYPTO 2024] for the purpose of…
We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries.…
The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…
Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises…
A recent and exciting thread of work focuses on developing methods for watermarking the output of large language models (LLMs). We focus on provably undetectable watermarking-that is, schemes that do not alter the output distribution of the…
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…
Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…
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…
Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it is being used to train such machine learning models or when distinguishing…
We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this paper, we propose a rigorous theoretical framework to…
The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages…
We present the first in depth study on the robustness of existing watermarking techniques applied to code generated by large language models (LLMs). As LLMs increasingly contribute to software development, watermarking has emerged as a…
Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns and has been widely deployed in industry. However,…
Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge in the domain lies in preserving the distribution of original…