THE SURVEY ON WATERMARKING METHODS FOR PROACTIVE DEFENSE AGAINST DEEPFAKE
DOI:
https://doi.org/10.28925/2663-4023.2026.32.1082Keywords:
deepfake, watermarking, image forensics, deep learning, steganography, information securityAbstract
As generative models advance, deepfake content is becoming indistinguishable from reality and passive forensic detection methods are becoming increasingly ineffective. The misuse of generative tools provide for adversaries opportunities for social engineering, disinformation campaigns and fraud. This requires a new class of forensics tools based on the preemptive marking of authentic content in order to defend it from being used for deepfake media generation or disinformation campaigns. In this survey we provide a comprehensive analysis of watermarking solutions for the purpose of proactive defense from deepfake. We identified most of the existing deepfake watermarking solutions in literature and provided taxonomy for them. Also we identified core metrics and datasets for training deep learning models for proactive defense watermarking. We make quantitative and qualitative comparisons of existing solutions, their methods, metrics and purposes. In the end we provide a summary of open problems and challenges in the field. This survey lays a foundation for future development of proactive deepfake defense methods and policies for generative AI compliance.
Downloads
References
Rijsbosch, B., van Dijck, G., & Kollnig, K. (2025). Adoption of watermarking measures for AI-generated content and implications under the EU AI Act. arXiv. https://arxiv.org/abs/2503.18156
Fernandez, P., Level, A., & Furon, T. (2024). What lies ahead for generative AI watermarking. In ICML 2024 Workshop on Generative AI and Law.
Nemecek, A., Jiang, Y., & Ayday, E. (2025). Watermarking without standards is not AI governance. arXiv. https://arxiv.org/abs/2505.23814
Tilo, D. (2025, April 9). Singapore firm nearly lost $500,000 after deepfake video scam: Police. HRD Asia. https://www.hcamag.com/asia/specialisation/hr-technology/singapore-firm-nearly-lost-500000-after-deepfake-video-scam-police/531450
Hu, Y., Jiang, Z., Guo, M., & Gong, N. Z. (2024). A transfer attack to image watermarks. arXiv. https://arxiv.org/abs/2403.15365
Kassis, A., & Hengartner, U. (2025). UnMarker: A universal attack on defensive image watermarking. In Proceedings of the IEEE Symposium on Security and Privacy (pp. 2602–2620). IEEE.
Yang, Y., Liang, C., He, H., Cao, X., & Gong, N. Z. (2021). FaceGuard: Proactive deepfake detection. arXiv. https://arxiv.org/abs/2109.05673
Zhao, Y., Liu, B., Ding, M., Liu, B., Zhu, T., & Yu, X. (2023). Proactive deepfake defence via identity watermarking. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 4602–4611).
Wang, T., Huang, M., Cheng, H., Zhang, X., & Shen, Z. (2024). LampMark: Proactive deepfake detection via training-free landmark perceptual watermarks. In Proceedings of the ACM International Conference on Multimedia (pp. 10515–10524).
Lan, S., Liu, K., Zhao, Y., Yang, C., Wang, Y., Yao, X., & Zhu, L. (2024). Facial features matter: A dynamic watermark-based proactive deepfake detection approach. arXiv. https://arxiv.org/abs/2411.14798
Wang, R., Juefei-Xu, F., Guo, Q., Huang, Y., Ma, L., Liu, Y., & Wang, L. (2020). DeepTag: Robust image tagging for deepfake provenance. arXiv. https://arxiv.org/abs/2009.09869
Wang, R., Juefei-Xu, F., Luo, M., Liu, Y., & Wang, L. (2021). FakeTagger: Robust safeguards against deepfake dissemination via provenance tracking. In Proceedings of the ACM International Conference on Multimedia (pp. 3546–3555).
Yu, N., Skripniuk, V., Abdelnabi, S., & Fritz, M. (2021). Artificial fingerprinting for generative models: Rooting deepfake attribution in training data. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 14448–14457).
Sun, P., Qi, H., Li, Y., & Lyu, S. (2023). FakeTracer: Catching face-swap deepfakes via implanting traces in training. arXiv. https://arxiv.org/abs/2307.14593
Sanjalawe, Y., Al-E’mari, S., Fraihat, S., Abualhaj, M., & Alzubi, E. (2025). A deep learning-driven multi-layered steganographic approach for enhanced data security. Scientific Reports, 15(1), 4761.
Wang, T., Huang, M., Cheng, H., Ma, B., & Wang, Y. (2023). Robust identity perceptual watermark against deepfake face swapping. arXiv. https://arxiv.org/abs/2311.01357
Wu, X., Liao, X., & Ou, B. (2023). SepMark: Deep separable watermarking for unified source tracing and deepfake detection. In Proceedings of the ACM International Conference on Multimedia (pp. 1190–1201).
Saberi, M., Sadasivan, V. S., Rezaei, K., Kumar, A., Chegini, A., Wang, W., & Feizi, S. (2023). Robustness of AI-image detectors: Fundamental limits and practical attacks. arXiv. https://arxiv.org/abs/2310.00076
Fairoze, J., Ortiz-Jimenez, G., Vecerik, M., Jha, S., & Gowal, S. (2025). On the difficulty of constructing a robust and publicly-detectable watermark. arXiv. https://arxiv.org/abs/2502.04901
Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., & Kumar, S. (2024). Rethinking FID: Towards a better evaluation metric for image generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9307–9315).
Neekhara, P., Hussain, S., Zhang, X., Huang, K., McAuley, J., & Koushanfar, F. (2024). FaceSigns: Semi-fragile watermarks for media authentication. ACM Transactions on Multimedia Computing, Communications and Applications, 20(11), 1–21.
Lai, Z., Yao, Z., Lai, G., Wang, C., & Feng, R. (2024). A novel face swapping detection scheme using the pseudo Zernike transform-based robust watermarking. Electronics, 13(24), 4955.
Tang, L., Ye, Q., Hu, H., Xue, Q., Xiao, Y., & Li, J. (2024). DeepMark: A scalable and robust framework for deepfake video detection. ACM Transactions on Privacy and Security, 27(1), 1–26.
Noreen, I., Muneer, M. S., & Gillani, S. (2022). Deepfake attack prevention using steganography GANs. PeerJ Computer Science, 8, e1125.
Beuve, N., Hamidouche, W., & Déforges, O. (2023). WaterLo: Protect images from deepfakes using localized semi-fragile watermark. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 393–402).
Nadimpalli, A. V., & Rattani, A. (2024). Social media authentication and combating deepfakes using semi-fragile invisible image watermarking. Digital Threats: Research and Practice, 5(4), 1–30.
Sun, C., Sun, H., Guo, Z., Diao, Y., Wang, L., Ma, D., et al. (2025). DiffMark: Diffusion-based robust watermark against deepfakes. arXiv. https://arxiv.org/abs/2507.01428
Walczyna, T., Zurada, J. M., & Piotrowski, Z. (2025). RE-Mark: An identity-recovery watermarking method for undoing deepfake face-swap. Authorea Preprints.
Wang, T., Cheng, H., Liu, M. H., & Kankanhalli, M. (2025). FractalForensics: Proactive deepfake detection and localization via fractal watermarks. In Proceedings of the ACM International Conference on Multimedia (pp. 7210–7219).
Shoaib, M. R., Wang, Z., Ahvanooey, M. T., & Zhao, J. (2023). Deepfakes, misinformation, and disinformation in the era of frontier AI. In Proceedings of the International Conference on Computer and Applications (ICCA) (pp. 1–7). IEEE.
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Михайло Марчук, Віталій Лукічов
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
