Key result
Remote heart rate estimation using 3D CDCAN achieves ~99% accuracy in deepfake detection.
Why the study?
As GAN-based deepfakes become increasingly mature and realistic, effective detectors are needed, leveraging disrupted normal pulse rhythms in manipulated videos.
A novel deepfake detection method utilizing remote heart rate estimation via 3D CDCAN demonstrated high accuracy on standard video datasets.
High-accuracy rPPG-based deepfake detection supports method refinement; leaves open validation in cardiovascular telehealth videos.
Objective: As GAN-based deepfakes have become increasingly mature and realistic, the demand for effective deepfake detectors has become essential. We are inspired by the fact that normal pulse rhythms present in real-face video can be decreased or even completely interrupted in a deepfake video; thus, we have introduced a new deepfake detection approach based on remote heart rate estimation using the 3D Central Difference Convolution Attention Network (CDCAN). Methods: Our proposed fake detector is mainly composed of a 3D CDCAN with an inverse attention mechanism and LSTM architecture. It utilizes 3D central difference convolution to enhance the spatiotemporal representation, which can capture rich physiological-related temporal context by gathering the time difference information. The soft attention mechanism is to focus on the skin region of interest, while the inverse attention mechanism is to further denoise rPPG signals. Results: The performance of our approach is evaluated on the two latest Celeb-DF and DFDC datasets, for which the experiment results show that our proposed approach achieves an accuracy of 99.5% and 97.4%, respectively. Conclusion: Our approach outperforms the state-of-art methods and proves the effectiveness of our DeepFake detector.
No takes yet. Share an insight, caveat, or question.
Feng et al. (2023) studied Deepfake detection. 3D Central Difference Convolution Attention Network (CDCAN) vs. State-of-art methods was evaluated on Accuracy on Celeb-DF and DFDC datasets. A deepfake detection approach based on remote heart rate estimation using 3D CDCAN achieved an accuracy of 99.5% on the Celeb-DF dataset and 97.4% on the DFDC dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: