Related papers: PRO: Enabling Precise and Robust Text Watermark fo…

Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key. Robustness is a core security…

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-specific downstream datasets, which makes it hard to claim the…

Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as the fundamental unit. However, existing methods still lack…

Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the…

With the application of vertical domain pre-trained language models (VPLMs) in specialized fields such as medical, finance, and law, model parameters and inference capabilities have become important digital assets. Achieving traceable…

Large Language Models (LLMs) are widely used in complex natural language processing tasks but raise privacy and security concerns due to the lack of identity recognition. This paper proposes a multi-party credible watermarking framework…

Detecting whether copyright holders' works were used in LLM pretraining is poised to be an important problem. This work proposes using data watermarks to enable principled detection with only black-box model access, provided that the…

The widespread use of Large Language Models (LLMs), celebrated for their ability to generate human-like text, has raised concerns about misinformation and ethical implications. Addressing these concerns necessitates the development of…

Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image…

Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying…

The advancements in audio generative models have opened up new challenges in their responsible disclosure and the detection of their misuse. In response, we introduce a method to watermark latent generative models by a specific watermarking…

The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models, making it a promising tool for preventing…

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…

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time watermarking, to protect…

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

Watermarking has recently emerged as an effective strategy for detecting the generations of large language models (LLMs). The strength of a watermark typically depends strongly on the entropy afforded by the language model and the set of…

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…

We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output using rejection…

Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among LLM providers, platforms, and end users, which manifest as…

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are…