Screen shooting resistant watermarking based on cross attention
Abstract With the development of digital imaging devices, the process of recording sensitive information displayed on screens through mobile phones and cameras has become a prominent technique for modern data leaks. In order to identify the origin of information violations, Screen-Shooting Resistant...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-00912-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850132750641659904 |
|---|---|
| author | Lianshan Liu Peng Xu Qianwen Xue |
| author_facet | Lianshan Liu Peng Xu Qianwen Xue |
| author_sort | Lianshan Liu |
| collection | DOAJ |
| description | Abstract With the development of digital imaging devices, the process of recording sensitive information displayed on screens through mobile phones and cameras has become a prominent technique for modern data leaks. In order to identify the origin of information violations, Screen-Shooting Resistant Watermarking (SSRW) has attracted a lot of attention. Most existing solutions are based on Convolutional Neural Networks (CNNs) for the embedding of watermarks. However, due to the limited reception field of CNNs, they are proficient in extracting local features but cannot understand the entire image. This paper presents a new watermarking system that is resistant to screen recording, with multi-head and cross-attention to incorporate watermarks, replacing the encoder in the end-to-end architecture. Specifically, we segment the image and watermark into smaller patches for positional embedding. Afterward, we calculate the attention scores through multi-head attention layers and generate the encoded image through concatenation. This approach increases the model’s ability to comprehend the entire image, thereby increasing performance. In addition, we enhance the U-Net network structure to replace the end-to-end decoder. The experimental results demonstrate that the proposed method not only reaches more than 95% accuracy in different capture scenarios but also excels in terms of reliability and invisibility relative to current state-of-the-art (SOTA) methods. In addition, this approach yields impressive PSNR and SSIM average values of 41.90 dB and 0.99, showing the excellent visual quality and reliability of the watermarked images. |
| format | Article |
| id | doaj-art-5e2ef0b81fb84092881fbcf04e73b547 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-5e2ef0b81fb84092881fbcf04e73b5472025-08-20T02:32:08ZengNature PortfolioScientific Reports2045-23222025-05-0115111510.1038/s41598-025-00912-8Screen shooting resistant watermarking based on cross attentionLianshan Liu0Peng Xu1Qianwen Xue2College of Computer Science and Engineering, Shandong University of Science and TechnologyCollege of Computer Science and Engineering, Shandong University of Science and TechnologyQingdao Maternal & Child Health and Family Planning Service CenterAbstract With the development of digital imaging devices, the process of recording sensitive information displayed on screens through mobile phones and cameras has become a prominent technique for modern data leaks. In order to identify the origin of information violations, Screen-Shooting Resistant Watermarking (SSRW) has attracted a lot of attention. Most existing solutions are based on Convolutional Neural Networks (CNNs) for the embedding of watermarks. However, due to the limited reception field of CNNs, they are proficient in extracting local features but cannot understand the entire image. This paper presents a new watermarking system that is resistant to screen recording, with multi-head and cross-attention to incorporate watermarks, replacing the encoder in the end-to-end architecture. Specifically, we segment the image and watermark into smaller patches for positional embedding. Afterward, we calculate the attention scores through multi-head attention layers and generate the encoded image through concatenation. This approach increases the model’s ability to comprehend the entire image, thereby increasing performance. In addition, we enhance the U-Net network structure to replace the end-to-end decoder. The experimental results demonstrate that the proposed method not only reaches more than 95% accuracy in different capture scenarios but also excels in terms of reliability and invisibility relative to current state-of-the-art (SOTA) methods. In addition, this approach yields impressive PSNR and SSIM average values of 41.90 dB and 0.99, showing the excellent visual quality and reliability of the watermarked images.https://doi.org/10.1038/s41598-025-00912-8Robust watermarkingScreen-shootingDeep learningCross attention |
| spellingShingle | Lianshan Liu Peng Xu Qianwen Xue Screen shooting resistant watermarking based on cross attention Scientific Reports Robust watermarking Screen-shooting Deep learning Cross attention |
| title | Screen shooting resistant watermarking based on cross attention |
| title_full | Screen shooting resistant watermarking based on cross attention |
| title_fullStr | Screen shooting resistant watermarking based on cross attention |
| title_full_unstemmed | Screen shooting resistant watermarking based on cross attention |
| title_short | Screen shooting resistant watermarking based on cross attention |
| title_sort | screen shooting resistant watermarking based on cross attention |
| topic | Robust watermarking Screen-shooting Deep learning Cross attention |
| url | https://doi.org/10.1038/s41598-025-00912-8 |
| work_keys_str_mv | AT lianshanliu screenshootingresistantwatermarkingbasedoncrossattention AT pengxu screenshootingresistantwatermarkingbasedoncrossattention AT qianwenxue screenshootingresistantwatermarkingbasedoncrossattention |