WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912993877426176 |
|---|---|
| author | He, Ziyuan Guo, Zhiqing Wang, Liejun Yang, Gaobo Diao, Yunfeng Ma, Dan |
| author_facet | He, Ziyuan Guo, Zhiqing Wang, Liejun Yang, Gaobo Diao, Yunfeng Ma, Dan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08614 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks He, Ziyuan Guo, Zhiqing Wang, Liejun Yang, Gaobo Diao, Yunfeng Ma, Dan Computer Vision and Pattern Recognition 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. |
| title | WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.08614 |