中文
相关论文

相关论文: UniMark: Unified Adaptive Multi-bit Watermarking f…

200 篇论文

Generative models have enabled easy creation and generation of images of all kinds given a single prompt. However, this has also raised ethical concerns about what is an actual piece of content created by humans or cameras compared to…

密码学与安全 · 计算机科学 2024-12-31 Aryaman Shaan , Garvit Banga , Raghav Mantri

The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking, embedding a signature into the generative model's synthesis…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Anirudh Nakra , Min Wu

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.…

密码学与安全 · 计算机科学 2025-04-23 Sam Gunn , Xuandong Zhao , Dawn Song

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…

密码学与安全 · 计算机科学 2026-02-18 Huijia Lin , Kameron Shahabi , Min Jae Song

Artificial Intelligence (AI) has found wide application, but also poses risks due to unintentional or malicious tampering during deployment. Regular checks are therefore necessary to detect and prevent such risks. Fragile watermarking is a…

密码学与安全 · 计算机科学 2023-09-06 Zhenzhe Gao , Zhaoxia Yin , Hongjian Zhan , Heng Yin , Yue Lu

Recent years have seen a surge in interest in digital content watermarking techniques, driven by the proliferation of generative models and increased legal pressure. With an ever-growing percentage of AI-generated content available online,…

Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, application of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we…

As Retrieval-Augmented Generation (RAG) evolves into service-oriented platforms (Rag-as-a-Service) with shared knowledge bases, protecting the copyright of contributed data becomes essential. Existing watermarking methods in RAG focus…

密码学与安全 · 计算机科学 2026-03-03 Tianyu Chen , Jian Lou , Wenjie Wang

In the watermark detection scenario, also known as zero-bit watermarking, a watermark, carrying no hidden message, is inserted in content. The watermark detector checks for the presence of this particular weak signal in content. The article…

多媒体 · 计算机科学 2007-05-23 Teddy Furon

Watermarking has become a plausible candidate for ownership verification and intellectual property protection of deep neural networks. Regarding image classification neural networks, current watermarking schemes uniformly resort to backdoor…

密码学与安全 · 计算机科学 2022-04-12 Fangqi Li , Shilin Wang

Current image watermarking technologies are predominantly categorized into text watermarking techniques and image steganography; however, few methods can simultaneously handle text and image-based watermark data, which limits their…

多媒体 · 计算机科学 2025-06-03 ZhongLi Fang , Yu Xie , Ping Chen

As large language models (LLMs) become integral to applications such as question answering and content creation, reliable content attribution has become increasingly important. Watermarking is a promising approach, but most existing methods…

密码学与安全 · 计算机科学 2026-05-11 Ya Jiang , Massieh Kordi Boroujeny , Surender Suresh Kumar , Kai Zeng

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…

计算与语言 · 计算机科学 2024-02-27 Massieh Kordi Boroujeny , Ya Jiang , Kai Zeng , Brian Mark

As valuable digital assets, deep neural networks necessitate robust ownership protection, positioning neural network watermarking (NNW) as a promising solution. Among various NNW approaches, weight-based methods are favored for their…

密码学与安全 · 计算机科学 2025-11-27 Yuan Yao , Jin Song , Jian Jin

The rapid growth of digital and AI-generated images has amplified the need for secure and verifiable methods of image attribution. While digital watermarking offers more robust protection than metadata-based approaches--which can be easily…

密码学与安全 · 计算机科学 2026-02-16 Tong Zhou , Ruyi Ding , Gaowen Liu , Charles Fleming , Ramana Rao Kompella , Yunsi Fei , Xiaolin Xu , Shaolei Ren

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…

密码学与安全 · 计算机科学 2026-05-29 Yuexin Li , Wenjie Qu , Linyu Wu , Yulin Chen , Yufei He , Tri Cao , Bryan Hooi , Jiaheng Zhang

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…

密码学与安全 · 计算机科学 2024-10-25 Miranda Christ , Sam Gunn , Tal Malkin , Mariana Raykova

Audio watermarking is widely used for leaking source tracing. The robustness of the watermark determines the traceability of the algorithm. With the development of digital technology, audio re-recording (AR) has become an efficient and…

声音 · 计算机科学 2023-04-04 Chang Liu , Jie Zhang , Han Fang , Zehua Ma , Weiming Zhang , Nenghai Yu

The proliferation of AI-generated content brings significant concerns on the forensic and security issues such as source tracing, copyright protection, etc, highlighting the need for effective watermarking technologies. Font-based text…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Kahim Wong , Jicheng Zhou , Kemou Li , Yain-Whar Si , Xiaowei Wu , Jiantao Zhou

The availability of bandwidth for internet access is sufficient enough to communicate digital assets. These digital assets are subjected to various types of threats. [19] As a result of this, protection mechanism required for the protection…

多媒体 · 计算机科学 2013-01-23 Mahimn Pandya , Hiren Joshi , Ashish Jani