Related papers: BiMark: Unbiased Multilayer Watermarking for Large…

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…

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

With the rapid development of cloud-based services, large language models have become increasingly accessible through various web platforms. However, this accessibility has also led to growing risks of model abuse. LLM watermarking has…

Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-resource languages. We…

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…

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…

Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construct a green/red token list and assign higher or lower…

As diffusion models (DMs) enable photorealistic image generation at unprecedented scale, watermarking techniques have become essential for provenance establishment and accountability. Existing methods face challenges: sampling-based…

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…

The strong general capabilities of Large Language Models (LLMs) bring potential ethical risks if they are unrestrictedly accessible to malicious users. Token-level watermarking inserts watermarks in the generated texts by altering the token…

Text watermarking technology aims to tag and identify content produced by large language models (LLMs) to prevent misuse. In this study, we introduce the concept of cross-lingual consistency in text watermarking, which assesses the ability…

This paper considers the problem of multi-bit generative watermarking for large language models under a worst-case false-alarm constraint. Prior work established a lower bound on the achievable miss-detection probability in the finite-token…

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

Watermarking language models is essential for distinguishing between human and machine-generated text and thus maintaining the integrity and trustworthiness of digital communication. We present a novel green/red list watermarking approach…

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…

Modern generative diffusion models rely on vast training datasets, often including images with uncertain ownership or usage rights. Radioactive watermarks -- marks that transfer to a model's outputs -- can help detect when such unauthorized…

Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive…

Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…

Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-written content from LLM-generated text. While most existing studies focus on determining whether…

We study multi-bit watermarking for data generated by stochastic processes, where a hidden message is embedded during sampling and must be decodable by an authorized detector that possesses side information unavailable to unauthorized…