Artificial intelligence content detection techniques using watermarking: A survey

IF 4.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Image and Vision Computing Pub Date : 2025-09-15 DOI:10.1016/j.imavis.2025.105728

Nishant Kumar, Amit Kumar Singh

{"title":"Artificial intelligence content detection techniques using watermarking: A survey","authors":"Nishant Kumar, Amit Kumar Singh","doi":"10.1016/j.imavis.2025.105728","DOIUrl":null,"url":null,"abstract":"<div><div>The rapid advancement in AI-generated content has catalyzed artistic creation, advertising, and media dissemination. Despite their widespread applications across several domains, AI-generated content inherently poses risks of identity fraud, copyright violation and unauthorized use. Watermarking has emerged as a critical tool for copyright protection, allowing embedding of identification information in AI-generated content, and enhances traceability and verification without hurting user experience. In this study, we provide a systematic literature review of the technique for detecting AI content, especially text and images, using watermarking, spanning studies from 2010 to 2025. Studies included in this review were peer-reviewed articles that applied watermarking to effectively distinguish AI-generated content from real or human-written content. We report strong past and current approaches to detecting watermarking-based AI content, especially text and images. This includes an analysis of how watermarking methods are used on AI-generated content, their role in enhancing performance, and a detail comparative analysis of notable techniques. Furthermore, we discuss how these methods have been evaluated, identify the research gaps and potential solutions. Our findings provide valuable insights for future watermarking-based AI content detection researchers, applications and organizations seeking to implement watermarking solutions in potential applications. To the best of our knowledge, we are the first to explore the detection of AI content, especially text and image, detection using watermarking.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"163 ","pages":"Article 105728"},"PeriodicalIF":4.2000,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Image and Vision Computing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0262885625003166","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

The rapid advancement in AI-generated content has catalyzed artistic creation, advertising, and media dissemination. Despite their widespread applications across several domains, AI-generated content inherently poses risks of identity fraud, copyright violation and unauthorized use. Watermarking has emerged as a critical tool for copyright protection, allowing embedding of identification information in AI-generated content, and enhances traceability and verification without hurting user experience. In this study, we provide a systematic literature review of the technique for detecting AI content, especially text and images, using watermarking, spanning studies from 2010 to 2025. Studies included in this review were peer-reviewed articles that applied watermarking to effectively distinguish AI-generated content from real or human-written content. We report strong past and current approaches to detecting watermarking-based AI content, especially text and images. This includes an analysis of how watermarking methods are used on AI-generated content, their role in enhancing performance, and a detail comparative analysis of notable techniques. Furthermore, we discuss how these methods have been evaluated, identify the research gaps and potential solutions. Our findings provide valuable insights for future watermarking-based AI content detection researchers, applications and organizations seeking to implement watermarking solutions in potential applications. To the best of our knowledge, we are the first to explore the detection of AI content, especially text and image, detection using watermarking.

查看原文本刊更多论文

基于水印的人工智能内容检测技术综述

人工智能生成内容的快速发展催化了艺术创作、广告和媒体传播。尽管人工智能生成的内容在多个领域得到了广泛的应用，但它本身就存在身份欺诈、侵犯版权和未经授权使用的风险。水印已经成为版权保护的重要工具，它允许在人工智能生成的内容中嵌入识别信息，并在不损害用户体验的情况下增强可追溯性和验证性。在本研究中，我们对使用水印检测人工智能内容（特别是文本和图像）的技术进行了系统的文献综述，涵盖了2010年至2025年的研究。本综述中包括的研究是同行评议的文章，这些文章应用水印来有效区分人工智能生成的内容与真实或人类编写的内容。我们报告了过去和现在强有力的方法来检测基于水印的人工智能内容，特别是文本和图像。这包括对如何在人工智能生成的内容上使用水印方法的分析，它们在提高性能方面的作用，以及对重要技术的详细比较分析。此外，我们讨论了如何评估这些方法，确定研究差距和潜在的解决方案。我们的研究结果为未来基于水印的人工智能内容检测研究人员、应用程序和组织寻求在潜在应用中实施水印解决方案提供了有价值的见解。据我们所知，我们是第一个探索人工智能内容的检测，特别是文本和图像，使用水印检测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Image and Vision Computing 工程技术-工程：电子与电气

CiteScore

8.50

自引率

8.50%

发文量

143

审稿时长

7.8 months

期刊介绍： Image and Vision Computing has as a primary aim the provision of an effective medium of interchange for the results of high quality theoretical and applied research fundamental to all aspects of image interpretation and computer vision. The journal publishes work that proposes new image interpretation and computer vision methodology or addresses the application of such methods to real world scenes. It seeks to strengthen a deeper understanding in the discipline by encouraging the quantitative comparison and performance evaluation of the proposed methodology. The coverage includes: image interpretation, scene modelling, object recognition and tracking, shape analysis, monitoring and surveillance, active vision and robotic systems, SLAM, biologically-inspired computer vision, motion analysis, stereo vision, document image understanding, character and handwritten text recognition, face and gesture recognition, biometrics, vision-based human-computer interaction, human activity and behavior understanding, data fusion from multiple sensor inputs, image databases.