Semi-Supervised Deep Domain Adaptation for Deepfake Detection

Md Shamim Seraj, Ankita Singh, Shayok Chakraborty; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2024, pp. 1061-1071

With the advent and popularity of generative models such as GANs, synthetic image generation and manipulation has become commonplace. This has promoted active research in the development of effective deepfake detection technology. While existing detection techniques have demonstrated promise, their performance suffers when tested on data generated using a different faking technology, on which the model has not been sufficiently trained. This challenge of detecting new types of deepfakes, without losing its prior knowledge about deepfakes (catastrophic forgetting), is of utmost importance in today's world. In this paper, we propose a novel deep domain adaptation framework to address this important problem in deepfake detection research. Our framework can leverage a large amount of labeled data (fake / genuine) generated using a particular faking technique (source domain) and a small amount of labeled data generated using a different faking technique (target domain) to induce a deep neural network with good generalization capability on both the source and the target domains. Further, deep neural networks are data-hungry and require a large amount of labeled training data, which may not always be available in the context of deepfake detection; our framework can also efficiently utilize unlabeled data in the target domain, which is more readily available than labeled data. We design a novel loss function and use the stochastic gradient descent (SGD) method to optimize the loss and train the deep network. Our extensive empirical studies on the benchmark FaceForensics++ dataset, using three types of deepfakes, corroborate the promise and potential of our framework against competing baselines.