Integration of Invisible Watermarking Based on a Hybrid DWT-SVD Approach in AI-Based Image Generators for Content Authentication

Authors

  • Herlina Harahap Universitas Harapan Medan
  • Imran Lubis Universitas Harapan Medan

DOI:

10.33395/sinkron.v10i3.16012

Keywords:

AI-image generator, Invisible Watermarking, Hybrid DWT–SVD, Digital Content Validation, Robustness

Abstract

The rapid advancement of artificial intelligence (AI) in the field of image generation has raised new challenges for digital content authentication and validity. AI-generated images are often indistinguishable from real photographs, creating potential risks of misuse in disinformation, visual manipulation, and copyright infringement. This study proposes the integration of an invisible watermarking method based on a hybrid of Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD) directly into the AI-image generation pipeline. The system is developed end-to-end with three main components: a Translator API to support Indonesian text inputs, an AI-image generator to create images from descriptive text, and a watermarking module to embed and extract hidden watermarks automatically.

Experimental results confirm that the visual quality of watermarked images was preserved, with PSNR values consistently above 35 dB and SSIM ≥ 0.95, indicating that the watermark is imperceptible to human vision. Watermark extraction evaluation achieved a position accuracy of 59.43% after normalization and a subsequence accuracy of 80.20%, demonstrating reliable recognition of the embedded watermark sequence. Robustness tests under common manipulations such as JPEG compression, rotation, cropping, and noise addition showed that the watermark remained detectable, although accuracy decreased under extreme cropping. These findings demonstrate that the hybrid DWT–SVD method is effective for ensuring the authenticity of AI-generated content without compromising visual quality, while offering novelty through its integration into the generative pipeline and its support for local language inputs.

GS Cited Analysis

Downloads

Download data is not yet available.

Author Biography

Imran Lubis, Universitas Harapan Medan

  •  

References

Abrar, I., & Sheikh, J. A. (2024). Robust Watermarking Scheme for Digital Image Authentication and Security. 2024 IEEE 21st India Council International Conference (INDICON), 1–6. https://doi.org/10.1109/INDICON63790.2024.10958465

Annadurai, C., Nelson, I., Devi, K. N., Manikandan, R., & Gandomi, A. H. (2023). Image Watermarking Based Data Hiding by Discrete Wavelet Transform Quantization Model with Convolutional Generative Adversarial Architectures. Applied Sciences, 13(2), 804. https://doi.org/10.3390/app13020804

Baskar, R., Dwibedi, R. K., Kumar, T. R., N, Vijayalakshmi., R, R. K., & Reddy, G. N. (2024). Digital Watermarking Techniques for Secure Image Distribution. 2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), 1–4. https://doi.org/10.1109/IITCEE59897.2024.10467416

Fang, H., Chen, K., Qiu, Y., Ma, Z., Zhang, W., & Chang, E.-C. (2024). DERO: Diffusion-Model-Erasure Robust Watermarking. Proceedings of the 32nd ACM International Conference on Multimedia, 2973–2981. https://doi.org/10.1145/3664647.3681220

Faustyna, F. (2025). Strategic optimization of artificial intelligence for marketing communications in the creative industry. Jurnal ASPIKOM, 10(1), 19. https://doi.org/10.24329/aspikom.v10i1.1589

Große, C., & Sundberg, L. (2025). Generative AI and digital resilience: a research agenda. Journal of Risk Research, 1–26. https://doi.org/10.1080/13669877.2025.2539105

Hur, H., Kang, M., Seo, S., & Hou, J.-U. (2024). Latent Diffusion Models for Image Watermarking: A Review of Recent Trends and Future Directions. Electronics, 14(1), 25. https://doi.org/10.3390/electronics14010025

Jayaram, Y., Sundar, D., & Bhat, J. (2024). Generative AI Governance & Secure Content Automation in Higher Education. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 5, 163–174. https://doi.org/10.63282/3050-9262.IJAIDSML-V5I4P116

Lei, L., Gai, K., Yu, J., Zhu, L., & Wu, Q. (2025). Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios. Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 7473–7481. https://doi.org/10.24963/ijcai.2025/831

Liao, C.-W., Chen, H.-W., Chen, B.-S., Wang, I.-C., Ho, W.-S., & Huang, W.-L. (2025). Exploring the Application of Text-to-Image Generation Technology in Art Education at Vocational Senior High Schools in Taiwan. Information, 16(5), 341. https://doi.org/10.3390/info16050341

Mareen, H., De Meulenaere, K., Lambert, P., & Van Wallendael, G. (2024). Diffusion Denoising Watermark Removal Models to Attack Invisible Image Watermarks. 2024 17th International Conference on Signal Processing and Communication System (ICSPCS), 1–6. https://doi.org/10.1109/ICSPCS63175.2024.10815799

Nightingale, S. J., & Farid, H. (2022). AI-synthesized faces are indistinguishable from real faces and more trustworthy. Proceedings of the National Academy of Sciences, 119(8). https://doi.org/10.1073/pnas.2120481119

Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021). Zero-Shot Text-to-Image Generation. In M. Meila & T. Zhang (Eds.), Proceedings of the 38th International Conference on Machine Learning (Vol. 139, pp. 8821–8831). PMLR. https://proceedings.mlr.press/v139/ramesh21a.html

Varghese, J., Razak, T. A., Hussain, O. Bin, & Subash, S. (2022). A hybrid digital image watermarking scheme incorporating DWT, DFT, DCT, and SVD transformations. Journal of Engineering Research (Kuwait), 10(1), 113–130. https://doi.org/10.36909/jer.9633

Xiang, Y., Wang, H., Yang, L., He, M., & Zhang, F. (2024). SEDD: Robust Blind Image Watermarking With Single Encoder And Dual Decoders. The Computer Journal, 67(6), 2390–2402. https://doi.org/10.1093/comjnl/bxae014

Xu, Y., & Mao, Y. (2024). A Robustness Improved Watermarking Scheme based on Invertible Neural Network. 2024 36th Chinese Control and Decision Conference (CCDC), 1304–1309. https://doi.org/10.1109/CCDC62350.2024.10587637

Downloads


Crossmark Updates

How to Cite

Harahap, H., & Lubis, I. (2026). Integration of Invisible Watermarking Based on a Hybrid DWT-SVD Approach in AI-Based Image Generators for Content Authentication. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 10(3), 1688-1698. https://doi.org/10.33395/sinkron.v10i3.16012