Edge-Aware Dual-Task Image Watermarking Against Social Network Noise
In the era of widespread digital image sharing on social media platforms, deep-learning-based watermarking has shown great potential in copyright protection. To address the fundamental trade-off between the visual quality of the watermarked image and the robustness of watermark extraction, we explor...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/57 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549427847725056 |
|---|---|
| author | Hao Jiang Jiahao Wang Yuhan Yao Xingchen Li Feifei Kou Xinkun Tang Limei Qi |
| author_facet | Hao Jiang Jiahao Wang Yuhan Yao Xingchen Li Feifei Kou Xinkun Tang Limei Qi |
| author_sort | Hao Jiang |
| collection | DOAJ |
| description | In the era of widespread digital image sharing on social media platforms, deep-learning-based watermarking has shown great potential in copyright protection. To address the fundamental trade-off between the visual quality of the watermarked image and the robustness of watermark extraction, we explore the role of structural features and propose a novel edge-aware watermarking framework. Our primary innovation lies in the edge-aware secret hiding module (EASHM), which achieves adaptive watermark embedding by aligning watermarks with image structural features. To realize this, the EASHM leverages knowledge distillation from an edge detection teacher and employs a dual-task encoder that simultaneously performs edge detection and watermark embedding through maximal parameter sharing. The framework is further equipped with a social network noise simulator (SNNS) and a secret recovery module (SRM) to enhance robustness against common image noise attacks. Extensive experiments on three public datasets demonstrate that our framework achieves superior watermark imperceptibility, with PSNR and SSIM values exceeding 40.82 dB and 0.9867, respectively, while maintaining an over 99% decoding accuracy under various noise attacks, outperforming existing methods by significant margins. |
| format | Article |
| id | doaj-art-1d7e1518fbcc41c0bf407c8713b3b91b |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-1d7e1518fbcc41c0bf407c8713b3b91b2025-01-10T13:14:18ZengMDPI AGApplied Sciences2076-34172024-12-011515710.3390/app15010057Edge-Aware Dual-Task Image Watermarking Against Social Network NoiseHao Jiang0Jiahao Wang1Yuhan Yao2Xingchen Li3Feifei Kou4Xinkun Tang5Limei Qi6Academy of Broadcasting Science, National Radio and Television Administration, Beijing 100866, ChinaSchool of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaAcademy of Broadcasting Science, National Radio and Television Administration, Beijing 100866, ChinaSchool of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, ChinaIn the era of widespread digital image sharing on social media platforms, deep-learning-based watermarking has shown great potential in copyright protection. To address the fundamental trade-off between the visual quality of the watermarked image and the robustness of watermark extraction, we explore the role of structural features and propose a novel edge-aware watermarking framework. Our primary innovation lies in the edge-aware secret hiding module (EASHM), which achieves adaptive watermark embedding by aligning watermarks with image structural features. To realize this, the EASHM leverages knowledge distillation from an edge detection teacher and employs a dual-task encoder that simultaneously performs edge detection and watermark embedding through maximal parameter sharing. The framework is further equipped with a social network noise simulator (SNNS) and a secret recovery module (SRM) to enhance robustness against common image noise attacks. Extensive experiments on three public datasets demonstrate that our framework achieves superior watermark imperceptibility, with PSNR and SSIM values exceeding 40.82 dB and 0.9867, respectively, while maintaining an over 99% decoding accuracy under various noise attacks, outperforming existing methods by significant margins.https://www.mdpi.com/2076-3417/15/1/57image watermarkingedge-aware optimizationmultitask learningknowledge distillationsocial network noisecopyright protection |
| spellingShingle | Hao Jiang Jiahao Wang Yuhan Yao Xingchen Li Feifei Kou Xinkun Tang Limei Qi Edge-Aware Dual-Task Image Watermarking Against Social Network Noise Applied Sciences image watermarking edge-aware optimization multitask learning knowledge distillation social network noise copyright protection |
| title | Edge-Aware Dual-Task Image Watermarking Against Social Network Noise |
| title_full | Edge-Aware Dual-Task Image Watermarking Against Social Network Noise |
| title_fullStr | Edge-Aware Dual-Task Image Watermarking Against Social Network Noise |
| title_full_unstemmed | Edge-Aware Dual-Task Image Watermarking Against Social Network Noise |
| title_short | Edge-Aware Dual-Task Image Watermarking Against Social Network Noise |
| title_sort | edge aware dual task image watermarking against social network noise |
| topic | image watermarking edge-aware optimization multitask learning knowledge distillation social network noise copyright protection |
| url | https://www.mdpi.com/2076-3417/15/1/57 |
| work_keys_str_mv | AT haojiang edgeawaredualtaskimagewatermarkingagainstsocialnetworknoise AT jiahaowang edgeawaredualtaskimagewatermarkingagainstsocialnetworknoise AT yuhanyao edgeawaredualtaskimagewatermarkingagainstsocialnetworknoise AT xingchenli edgeawaredualtaskimagewatermarkingagainstsocialnetworknoise AT feifeikou edgeawaredualtaskimagewatermarkingagainstsocialnetworknoise AT xinkuntang edgeawaredualtaskimagewatermarkingagainstsocialnetworknoise AT limeiqi edgeawaredualtaskimagewatermarkingagainstsocialnetworknoise |