Related papers: DMark: Order-Agnostic Watermarking for Diffusion L…

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…

Diffusion language models (DLMs) provide a bidirectional generation framework naturally suited for infilling, yet their performance is constrained by the pre-specified infilling length. In this paper, we reveal that DLMs possess an inherent…

As large language models (LLMs) reach human-like fluency, reliably distinguishing AI-generated text from human authorship becomes increasingly difficult. While watermarks already exist for LLMs, they often lack flexibility and struggle with…

Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding. This stems from the ''combinatorial contradiction'' phenomenon, where parallel tokens form…

Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly the GumbelMax-trick-based watermark(GM watermark), is a…

Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…

Robust invisible watermarking aims to embed hidden information into images such that the watermark can survive various image manipulations. However, the rise of powerful diffusion-based image generation and editing techniques poses a new…

Large language model (LLM)-based embedding models, benefiting from large scale pre-training and post-training, have begun to surpass BERT and T5-based models on general-purpose text embedding tasks such as document retrieval. However, a…

Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tracing and authenticating AI-generated content. However, existing methods rely on…

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…

As Diffusion Models (DM) generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the…

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.…

We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generation to restore output diversity, along with entropy-weighted scoring and multi-region…

This paper shows how diffusion language models (DLMs) can be used as effective and efficient retrievers. Existing DLM-based retrievers (e.g., DiffEmbed) follow BERT-style encoding, representing each query or passage as a single mean-pooled…

The proliferation of Large Language Models (LLMs) necessitates efficient mechanisms to distinguish machine-generated content from human text. While statistical watermarking has emerged as a promising solution, existing methods suffer from…

Text-to-Speech (TTS) diffusion models generate high-quality speech, which raises challenges for the model intellectual property protection and speech tracing for legal use. Audio watermarking is a promising solution. However, due to the…

In the present-day scenario, Large Language Models (LLMs) are establishing their presence as powerful instruments permeating various sectors of society. While their utility offers valuable support to individuals, there are multiple concerns…

Masked Diffusion Language Models (DLMs) have recently emerged as a promising alternative to traditional Autoregressive Models (ARMs). DLMs employ transformer encoders with bidirectional attention, enabling parallel token generation while…

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…

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…