1. Introduction
The term DeepFake has gained much attention in recent times. It denotes manipulated multimedia content, specifically video or images created using deep learning techniques. Deepfakes are typically created using generative networks like Variational Autoencoders (VAE) [24], and Generative Adversarial Networks (GAN) [13]. Although digital media manipulation is not new, the use of deep learning architectures for this purpose has been gaining popularity. Deepfake forgeries work by altering the facial attributes [16], gestures [4], or swapping the entire face of a target subject [26]. A deepfake generator first learns the facial features and attributes of the subjects and then generates a forged face by selectively altering these attributes.