Digital Watermarking Technology for AI-Generated Images: A Survey
The rapid advancement of AI-generated content (AIGC) has significantly improved the realism and accessibility of synthetic images. While large image generation models offer immense potential in creative industries, they also introduce serious challenges, including copyright infringement, content aut...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/4/651 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850238768284434432 |
|---|---|
| author | Huixin Luo Li Li Juncheng Li |
| author_facet | Huixin Luo Li Li Juncheng Li |
| author_sort | Huixin Luo |
| collection | DOAJ |
| description | The rapid advancement of AI-generated content (AIGC) has significantly improved the realism and accessibility of synthetic images. While large image generation models offer immense potential in creative industries, they also introduce serious challenges, including copyright infringement, content authentication, and the traceability of generated images. Digital watermarking has emerged as a promising approach to address these concerns by embedding imperceptible yet detectable signatures into generated images. This survey provides a comprehensive review of three core areas: (1) the evolution of image generation technologies, highlighting key milestones such as the transition from GANs to diffusion models; (2) traditional and state-of-the-art digital image watermarking algorithms, encompassing spatial domain, transform domain, and deep learning-based approaches; (3) watermarking methods specific to AIGC, including ownership authentication of AI model and diffusion model, and watermarking of AI-generated images. Additionally, we examine common performance evaluation metrics used in this field, such as watermark capacity, watermark detection accuracy, fidelity, and robustness. Finally, we discuss the unresolved issues and propose several potential directions for future research. We look forward to this paper offering valuable reference for academics in the field of AIGC watermarking and related fields. |
| format | Article |
| id | doaj-art-9f3bf16e258e43fc91e88238f325ba8a |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-9f3bf16e258e43fc91e88238f325ba8a2025-08-20T02:01:23ZengMDPI AGMathematics2227-73902025-02-0113465110.3390/math13040651Digital Watermarking Technology for AI-Generated Images: A SurveyHuixin Luo0Li Li1Juncheng Li2School of Communication and Information Engineering, Shanghai University, Shanghai 200444, ChinaSchool of Communication and Information Engineering, Shanghai University, Shanghai 200444, ChinaSchool of Communication and Information Engineering, Shanghai University, Shanghai 200444, ChinaThe rapid advancement of AI-generated content (AIGC) has significantly improved the realism and accessibility of synthetic images. While large image generation models offer immense potential in creative industries, they also introduce serious challenges, including copyright infringement, content authentication, and the traceability of generated images. Digital watermarking has emerged as a promising approach to address these concerns by embedding imperceptible yet detectable signatures into generated images. This survey provides a comprehensive review of three core areas: (1) the evolution of image generation technologies, highlighting key milestones such as the transition from GANs to diffusion models; (2) traditional and state-of-the-art digital image watermarking algorithms, encompassing spatial domain, transform domain, and deep learning-based approaches; (3) watermarking methods specific to AIGC, including ownership authentication of AI model and diffusion model, and watermarking of AI-generated images. Additionally, we examine common performance evaluation metrics used in this field, such as watermark capacity, watermark detection accuracy, fidelity, and robustness. Finally, we discuss the unresolved issues and propose several potential directions for future research. We look forward to this paper offering valuable reference for academics in the field of AIGC watermarking and related fields.https://www.mdpi.com/2227-7390/13/4/651digital image watermarkingimage securityAIGC watermarkingdeep learning |
| spellingShingle | Huixin Luo Li Li Juncheng Li Digital Watermarking Technology for AI-Generated Images: A Survey Mathematics digital image watermarking image security AIGC watermarking deep learning |
| title | Digital Watermarking Technology for AI-Generated Images: A Survey |
| title_full | Digital Watermarking Technology for AI-Generated Images: A Survey |
| title_fullStr | Digital Watermarking Technology for AI-Generated Images: A Survey |
| title_full_unstemmed | Digital Watermarking Technology for AI-Generated Images: A Survey |
| title_short | Digital Watermarking Technology for AI-Generated Images: A Survey |
| title_sort | digital watermarking technology for ai generated images a survey |
| topic | digital image watermarking image security AIGC watermarking deep learning |
| url | https://www.mdpi.com/2227-7390/13/4/651 |
| work_keys_str_mv | AT huixinluo digitalwatermarkingtechnologyforaigeneratedimagesasurvey AT lili digitalwatermarkingtechnologyforaigeneratedimagesasurvey AT junchengli digitalwatermarkingtechnologyforaigeneratedimagesasurvey |