Abstract: Over the last years, the increase in smartphones and social networks has made digital images and videos common digital objects. According to reports, almost two billion pictures are uploaded every day on the internet. This tremendous use of digital images has been followed by a rise of techniques to alter image contents, using editing software like Photoshop for instance. Fake videos and images created by deepFake techniques have become a great public issue recently. Nowadays several techniques for facial manipulation in videos have been successfully developed like Face Swap, deep Fake, etc. On one side, this technological advancement increase scope to new areas (e.g., movie making, visual effect, visual arts, etc.). On the other side, contradicting, it also increases the ease in the generation of video forgeries by malicious users. Therefore by using deep learning techniques we can detect the video is fake or not. In order to detect these malicious images, we are going to develop a system that can automatically detect and assess the integrity of digital visual media is therefore indispensable. Deepfake is a technique for human image synthesis based on artificial intelligence, i.e., to superimpose the existing (source) images or videos onto destination images or videos using neural networks (NNs). Deepfake enthusiasts have been using NNs to produce convincing face swaps. Deep fakes are a type of video or image forgery developed to spread misinformation, invade privacy, and mask the truth using advanced technologies such as trained algorithms, deep learning applications, and artificial intelligence. They have become a nuisance to social media users by publishing fake videos created by fusing a celebrity’s face over an explicit video. The impact of deepFakes is alarming, with politicians, senior corporate officers, and world leaders being targeted by nefarious actors. An approach to detect deepFake videos of politicians using temporal sequential frames is proposed. The proposed approach uses the forged video to extract the frames at the first level followed by a deep depth-based convolutional long short-term memory model to identify the fake frames at the second level. Also, the proposed model is evaluated on our newly collected ground truth dataset of forged videos using source and destination video frames of famous politicians. Experimental results demonstrate the effectiveness of ourmethod.
Keywords: Deepfake, Deep Learning, Deep fake Technology, Deep fake Detection, Forensic Verification, Fake Images, Fake Image Detection,Etc.
|
DOI:
10.17148/IJARCCE.2023.12615
