CVPR Findings2026
Watermarking Matters for Deepfake Detection: A Proactive Method for Detecting Forgeries under Conventional Attacks
Zhiqiu Xia, Furong Mu, Qi Li, Shanshan Zhang, Jie Gui, Chunpeng Wang, Yunan Liu
Abstract
Face deepfake detection is a crucial technique for verifying the authenticity of facial media content and has been a long-standing focus of research in the field of multimedia forensics. However, due to the increasing diversity of forgery techniques and the declining visual quality of forgeries, achieving consistently reliable detection results remains a significant challenge. To tackle this challenge, we propose a proactive approach that integrates watermarking techniques with knowledge distillation to enable robust and accurate deepfake detection. The proposed method is grounded in two key ideas: First, watermark information is embedded into the Quaternion Continuous Orthogonal Moments (QCOMs) space to balance imperceptibility and robustness. Specifically, during the testing phase, the integrity of the watermark remains intact under conventional attacks but is disrupted when deepfakes are introduced. Second, a dual-task learning framework is designed, consisting of a watermark extractor and a deepfake detector. Within this framework, lightweight multiscale adapters are introduced to transfer the forgery-related clues extracted by the watermark extractor to the detector, while preserving the independence of both components. Experimental results on benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance in cross-domain deepfake detection, exhibiting particularly strong robustness against various conventional attacks.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
- SimSwap: An Efficient Framework For High Fidelity Face Swapping cites FaceForensics++: Learning to Detect Manipulated Facial Images
Builds on28
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- FaceForensics++: Learning to Detect Manipulated Facial ImagesAndreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess et al.ICCV 2019 · 2,966 citations
- Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelLianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang et al.ICML 2024 · 1,725 citations
- WildDeepfake: A Challenging Real-World Dataset for Deepfake DetectionBojia Zi, Minghao Chang, Jingjing Chen, Xingjun Ma et al.ACM MM 2020 · 443 citations
- SimSwap: An Efficient Framework For High Fidelity Face SwappingRenwang Chen, Xuanhong Chen, Bingbing Ni, Yanhao GeACM MM 2020 · 409 citations
Related papers
- Toward Robust Deepfake Detection: A Proactive Method Based on Watermarking and Knowledge DistillationChunpeng Wang, Wenlong Ma, Li Zou, Zhiqiu Xia et al.ACM MM 2025
- SepVAMark: Deep Separable Visual-Audio Fusion Watermarking for Source Tracing and Deepfake DetectionChuan Zhang, Zihan Li, Zihao Xu, Xuhao Ren et al.ACM MM 2025 · 2 citations
- Proactive Deepfake Detection via Self-Verifiable Semantic WatermarkingPeiqi Jiang, Bohan Lei, Yuhao Sun, Lingyun Yu et al.ACM MM 2025
- ADD: Frequency Attention and Multi-View Based Knowledge Distillation to Detect Low-Quality Compressed Deepfake ImagesLe Minh Binh, Simon S. WooAAAI 2022 · 114 citations
- LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual WatermarksTianyi Wang, Mengxiao Huang, Harry Cheng, Xiao Zhang et al.ACM MM 2024 · 27 citations
