Detection of Synthesized Videos using CNN
R. Vijaya Saraswathi, Mihir Gadwalkar, Siddamsetty Srinivas Midhun, Gadkol Nandini Goud, Ashish Vidavaluri · 2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) · 2022
Deepfake refers to changing a person's face or their facial emotions. Many fake videos are being overused and going viral in a matter of seconds. Deep learning is used to generate fake videos and images. Deepfakes are synthetic media in which the people who appear there are not real. Increasingly sophisticated technology makes it difficult to distinguish between real and fake videos and images. This will make both men and women more concerned about their safety. It is essential to create a model that can distinguish between real and fake videos in order to maintain and respect everyone's right to privacy. In this research, a Deep Learning Approach is used to offer a framework to identify these Deepfake's, a convolutional neural network architecture will be trained using a database of faces that were taken out of a mixed dataset.