WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
This addresses privacy invasion and identity theft risks from deepfakes, but it is incremental as it builds on existing watermarking and GNN methods.
The paper tackles the problem of deepfake threats by proposing WaveGuard, a proactive watermarking framework that embeds watermarks in frequency domains and uses graph neural networks for structural consistency, achieving state-of-the-art performance in robustness and visual quality on face swap and reenactment tasks.
Deepfake technology poses increasing risks such as privacy invasion and identity theft. To address these threats, we propose WaveGuard, a proactive watermarking framework that enhances robustness and imperceptibility via frequency-domain embedding and graph-based structural consistency. Specifically, we embed watermarks into high-frequency sub-bands using Dual-Tree Complex Wavelet Transform (DT-CWT) and employ a Structural Consistency Graph Neural Network (SC-GNN) to preserve visual quality. We also design an attention module to refine embedding precision. Experimental results on face swap and reenactment tasks demonstrate that WaveGuard outperforms state-of-the-art methods in both robustness and visual quality. Code is available at https://github.com/vpsg-research/WaveGuard.