中文
相关论文

相关论文: Safe-Sora: Safe Text-to-Video Generation via Graph…

200 篇论文

Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content provenance and attribution. The growing complexity of digital…

计算机视觉与模式识别 · 计算机科学 2025-01-30 Aleksandar Petrov , Shruti Agarwal , Philip H. S. Torr , Adel Bibi , John Collomosse

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Shilin Lu , Zihan Zhou , Jiayou Lu , Yuanzhi Zhu , Adams Wai-Kin Kong

The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works to combat Deepfakes videos have developed detectors that are highly…

计算机视觉与模式识别 · 计算机科学 2024-06-17 Qingyuan Liu , Pengyuan Shi , Yun-Yun Tsai , Chengzhi Mao , Junfeng Yang

The ability to embed watermarks in images is a fundamental problem of interest for computer vision, and is exacerbated by the rapid rise of generated imagery in recent times. Current state-of-the-art techniques suffer from computational and…

图像与视频处理 · 电气工程与系统科学 2025-09-17 Vinay Shukla , Prachee Sharma , Ryan Rossi , Sungchul Kim , Tong Yu , Aditya Grover

This paper addresses copyright protection as a major security demand in digital marketplaces. Two watermarking techniques are proposed and compared for compressed and uncompressed video with the intention to show the advantages and the…

信息论 · 计算机科学 2009-12-10 Jamal Hussein , Aree Mohammed

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,…

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

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…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Yi Zhang , Hongbo Huang , Liang-Jie Zhang

Image generation algorithms are increasingly integral to diverse aspects of human society, driven by their practical applications. However, insufficient oversight in artificial Intelligence generated content (AIGC) can facilitate the spread…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Wenhao Luo , Zhangyi Shen , Ye Yao , Feng Ding , Guopu Zhu , Weizhi Meng

With the rapid rise of large models, copyright protection for generated image content has become a critical security challenge. Although deep learning watermarking techniques offer an effective solution for digital image copyright…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Shaowu Wu , Liting Zeng , Wei Lu , Xiangyang Luo

Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to…

As generative AI models produce increasingly realistic output, both academia and industry are focusing on the ability to detect whether an output was generated by an AI model or not. Many of the research efforts and policy discourse are…

密码学与安全 · 计算机科学 2025-04-21 Houssam Kherraz

Digital Watermarking is an extremely wide aspect of information security, either by its applications, by its properties, or by its designs. In particular, a lot of research has been made about video watermarking and it can make it quite…

图像与视频处理 · 电气工程与系统科学 2019-08-26 Romain Artru , Alexandre Gouaillard , Touradj Ebrahimi

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

Digital water marking is one of the essential fields in image security and copyright protection. The proposed technique in this paper was based on the principle of protecting images by hide an invisible watermark in the image. The technique…

计算机视觉与模式识别 · 计算机科学 2013-07-05 Firas A. Jassim

Digital watermarking system is a paramount for safeguarding valuable resources and information. Digital watermarks are generally imperceptible to the human eye and ear. Digital watermark can be used in video, audio and digital images for a…

密码学与安全 · 计算机科学 2012-05-30 Md. Selim Reza , Mohammed Shafiul Alam Khan , Md. Golam Robiul Alam , Serajul Islam

3D Gaussian Splatting (3DGS) has emerged as a pivotal technique for 3D scene representation, providing rapid rendering speeds and high fidelity. As 3DGS gains prominence, safeguarding its intellectual property becomes increasingly crucial…

密码学与安全 · 计算机科学 2024-12-10 Yuqi Tan , Xiang Liu , Shuzhao Xie , Bin Chen , Shu-Tao Xia , Zhi Wang

Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…

密码学与安全 · 计算机科学 2026-05-26 Zhenxin Ai , Haiyun He

The advancement in digital technologies have made it possible to produce perfect copies of digital content. In this environment, malicious users reproduce the digital content and share it without compensation to the content owner. Content…

多媒体 · 计算机科学 2016-10-11 Sachin Mehta , Balakrishnan Prabhakaran , Rajarathnam Nallusamy , Derrick Newton

Latent diffusion models have exhibited considerable potential in generative tasks. Watermarking is considered to be an alternative to safeguard the copyright of generative models and prevent their misuse. However, in the context of model…

密码学与安全 · 计算机科学 2025-02-20 Liangqi Lei , Keke Gai , Jing Yu , Liehuang Zhu , Qi Wu