CAPSULE-FORENSICS: USING CAPSULE NETWORKS TO DETECT FORGED IMAGES AND VIDEOS

Abstract: Attackers can now fabricate pictures and movies more easily because to advances in media production tools. A video downloaded from a social media can be used to make forgeries in real time.Although state-of-the-art Detecting fake photos and videos is a difficult task. This article use a capsule network to detect several types of spoofing attacks, ranging from replay attack employing graphics or scanned movies to deep convolutional neural network-generated bogus videos. It broadens the scope of capsule networks' use beyond their initial intent. We are working on the creation of a model that will be able to solve complex graphics problems. It will involve image datasets for training and testing. Terms used – capsule network, computer generated video, forgery detection replay attack