WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
- 4 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (4) , 4757-4770
Abstract
Deepfake technology has great potential in the field of media and entertainment, but it also brings serious risks, including privacy disclosure and identity fraud. To counter these threats, proactive forensic methods have become a research hotspot by embedding invisible watermark signals to build active protection schemes. However, existing methods are vulnerable to watermark destruction under malicious distortions, which leads to insufficient robustness. Moreover, embedding strong signals may degrade image quality, making it challenging to balance robustness and imperceptibility. Although watermarked images look natural, their underlying structures are often different from the original images, which is ignored by traditional watermarking methods. To address these issues, this paper proposes a proactive watermarking framework called WaveGuard, which explores frequency domain embedding and graph-based structural consistency optimization. In this framework, the watermark is embedded into the high-frequency sub-bands by dual-tree complex wavelet transform (DT-CWT) to enhance the robustness against distortions and deepfake forgeries. By leveraging joint sub-band correlations and selected sub-band combinations, the framework enables robust source tracing and semi-robust deepfake detection. To enhance imperceptibility, we propose a Structural Consistency Graph Neural Network (SC-GNN) that constructs graph representations of the original and watermarked images to ensure structural consistency and reduce perceptual artifacts. Experimental results show that the proposed method performs exceptionally well in face swap and face replay tasks. The code has been published at https://github.com/vpsg-research/WaveGuard.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62462060)
- National Natural Science Foundation of China (62302427)
- Natural Science Foundation of Xinjiang Uygur Autonomous Region (2023D01C175)
- Tianshan Talent Training Program (2022TSYCLJ0036)
This publication has 46 references indexed in Scilit:
- LEDNet: a multimodal foundation model for robust deepfake detectionScience China Information Sciences, 2025
- Convolutional neural network framework for deepfake detection: A diffusion-based approachComputer Vision and Image Understanding, 2025
- Generative Adversarial Nets2023
- Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping2022
- TAFIM: Targeted Adversarial Attacks Against Facial Image Manipulations2022
- StegaStamp: Invisible Hyperlinks in Physical Photographs2020
- Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems2020
- Light Field Messaging With Deep Photographic Steganography2019
- HiDDeN: Hiding Data With Deep Networks2018
- GANimation: Anatomically-Aware Facial Animation from a Single Image2018