DeepFake Detection using 3D-Xception Net with Discrete Fourier Transformation

The videos are more popular for sharing content on social media to capture the audience’s attention. artificial manipulation of is growing rapidly make flashy and interesting but they can easily misuse spread false information platforms. Deep Fake a problematic method in which components added video using emerging deep learning techniques. Due increase accuracy fake generation methods, artificially created no longer detectable pose major threat users. To address this problem, we have proposed new detecting 3D Inflated Xception Net with Discrete Fourier Transformation. was originally designed application 2D images only. first attempt use categorizing video-based data. advantage is, it works whole rather than subset frames while categorizing. Our model tested dataset Celeb-DF achieved better accuracy.