Towards Solving the DeepFake Problem : An Analysis on Improving DeepFake Detection using Dynamic Face Augmentation
This work improves deepfake detection for security and media verification, but it is incremental as it builds on existing methods with a new data augmentation approach.
The paper tackles the problem of deepfake detection by addressing dataset oversampling and overfitting, proposing a dynamic face augmentation method called Face-Cutout that reduces LogLoss by 15.2% to 35.3% compared to other techniques.
The creation of altered and manipulated faces has become more common due to the improvement of DeepFake generation methods. Simultaneously, we have seen detection models' development for differentiating between a manipulated and original face from image or video content. In this paper, we focus on identifying the limitations and shortcomings of existing deepfake detection frameworks. We identified some key problems surrounding deepfake detection through quantitative and qualitative analysis of existing methods and datasets. We found that deepfake datasets are highly oversampled, causing models to become easily overfitted. The datasets are created using a small set of real faces to generate multiple fake samples. When trained on these datasets, models tend to memorize the actors' faces and labels instead of learning fake features. To mitigate this problem, we propose a simple data augmentation method termed Face-Cutout. Our method dynamically cuts out regions of an image using the face landmark information. It helps the model selectively attend to only the relevant regions of the input. Our evaluation experiments show that Face-Cutout can successfully improve the data variation and alleviate the problem of overfitting. Our method achieves a reduction in LogLoss of 15.2% to 35.3% on different datasets, compared to other occlusion-based techniques. Moreover, we also propose a general-purpose data pre-processing guideline to train and evaluate existing architectures allowing us to improve the generalizability of these models for deepfake detection.