中文
相关论文

相关论文: METR: Image Watermarking with Large Number of Uniq…

200 篇论文

We revisit Tree-Ring Watermarking, a recent diffusion model watermarking method that demonstrates great robustness to various attacks. We conduct an in-depth study on it and reveal that the distribution shift unintentionally introduced by…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Hai Ci , Pei Yang , Yiren Song , Mike Zheng Shou

Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. In this paper, we introduce a novel technique called Tree-Ring Watermarking that robustly…

机器学习 · 计算机科学 2023-07-06 Yuxin Wen , John Kirchenbauer , Jonas Geiping , Tom Goldstein

Tree-Ring Watermarking is a significant technique for authenticating AI-generated images. However, its effectiveness in rectified flow-based models remains unexplored, particularly given the inherent challenges of these models with noise…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Ved Umrajkar , Aakash Kumar Singh

Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into generated tokens that either flags LLM-generated text (zero-bit watermarking) or encodes more…

机器学习 · 计算机科学 2026-05-25 Atefeh Gilani , Sajani Vithana , Carol Xuan Long , Oliver Kosut , Lalitha Sankar , Flavio P. Calmon

Digital watermarking is widely used for copyright protection. Traditional 3D watermarking approaches or commercial software are typically designed to embed messages into 3D meshes, and later retrieve the messages directly from…

计算机视觉与模式识别 · 计算机科学 2022-03-30 Innfarn Yoo , Huiwen Chang , Xiyang Luo , Ondrej Stava , Ce Liu , Peyman Milanfar , Feng Yang

We present a novel attack specifically designed against Tree-Ring, a watermarking technique for diffusion models known for its high imperceptibility and robustness against removal attacks. Unlike previous removal attacks, which rely on…

密码学与安全 · 计算机科学 2025-06-13 Junhua Lin , Marc Juarez

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

密码学与安全 · 计算机科学 2025-07-03 Haiyun He , Yepeng Liu , Ziqiao Wang , Yongyi Mao , Yuheng Bu

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

计算与语言 · 计算机科学 2026-05-29 Yukang Lin , Jiahao Shao , Shuoran Jiang , Wentao Zhu , Bingjie Lu , Xiangping Wu , Joanna Siebert , Qingcai Chen

Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and security risks. Dataset watermarking has been proposed to ensure…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Xincheng Wang , Hanchi Sun , Wenjun Sun , Kejun Xue , Wangqiu Zhou , Jianbo Zhang , Wei Sun , Dandan Zhu , Xiongkuo Min , Jun Jia , Zhijun Fang

Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Li Zhang , Shruti Agarwal , John Collomosse , Pengtao Xie , Vishal Asnani

Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider…

计算机视觉与模式识别 · 计算机科学 2021-01-27 Nicola Messina , Fabrizio Falchi , Andrea Esuli , Giuseppe Amato

Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent…

计算与语言 · 计算机科学 2026-04-17 Jiahao Xu , Rui Hu , Olivera Kotevska , Zikai Zhang

In this work, we introduce a novel deep learning-based approach to text-in-image watermarking, a method that embeds and extracts textual information within images to enhance data security and integrity. Leveraging the capabilities of deep…

多媒体 · 计算机科学 2024-04-23 Bishwa Karki , Chun-Hua Tsai , Pei-Chi Huang , Xin Zhong

Watermarking for diffusion images has drawn considerable attention due to the widespread use of text-to-image diffusion models and the increasing need for their copyright protection. Recently, advanced watermarking techniques, such as Tree…

密码学与安全 · 计算机科学 2025-04-21 Yaopeng Wang , Huiyu Xu , Zhibo Wang , Jiacheng Du , Zhichao Li , Yiming Li , Qiu Wang , Kui Ren

As large language models (LLMs) grow more powerful, concerns over copyright infringement of LLM-generated texts have intensified. LLM watermarking has been proposed to trace unauthorized redistribution or resale of generated content by…

密码学与安全 · 计算机科学 2025-08-05 Qihao Lin , Chen Tang , Lan zhang , Junyang zhang , Xiangyang Li

In this paper we present a novel deep framework for a watermarking - a technique of embedding a transparent message into an image in a way that allows retrieving the message from a (perturbed) copy, so that copyright infringement can be…

多媒体 · 计算机科学 2020-06-09 Marcin Plata , Piotr Syga

High-fidelity text-to-image diffusion models have revolutionized visual content generation, but their widespread use raises significant ethical concerns, including intellectual property protection and the misuse of synthetic media. To…

计算机视觉与模式识别 · 计算机科学 2025-08-21 Yunzhuo Chen , Naveed Akhtar , Nur Al Hasan Haldar , Ajmal Mian

The rapid advancement of generative AI has underscored the critical need for identifying image ownership and protecting copyrights. This makes post-processing image watermarking an essential tool -- it involves embedding a specific…

密码学与安全 · 计算机科学 2026-05-12 Xinyu Zhang , Ziping Dong , Qingyu Liu , Yuan Hong , Zhongjie Ba , Kui Ren

Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Natan Semyonov , Rami Puzis , Asaf Shabtai , Gilad Katz

Deep learning has been achieving top performance in many tasks. Since training of a deep learning model requires a great deal of cost, we need to treat neural network models as valuable intellectual properties. One concern in such a…

密码学与安全 · 计算机科学 2019-01-21 Ryota Namba , Jun Sakuma
‹ 上一页 1 2 3 10 下一页 ›