The digital world has been witnessing a fast progress in technology, which led to an enormous increase in using digital devices, such as cell phones, laptops, and digital cameras. Thus, photographs and videos function as the primary sources of legal proof in courtrooms concerning any incident or crime. It has become important to prove the trustworthiness of digital multimedia. Inter-frame video forgery one of common types of video manipulation performed in temporal domain. It deals with inter-frame video forgery detection that involves frame deletion, insertion, duplication, and shuffling. Deep Learning (DL) techniques have been proven effective in analysis and processing of visual media. Dealing with video data needs to handle the third dimension (the time dimension), which means extracting temporal features as well as spatial features. The proposed model is built based on the Three Dimension Convolution Neural Network (3D-CNN). Through pre-processing operation that introduced difference frames that pick up the difference in successive adjacent frames, which provide a large quantity of temporal information and lead to enhance the effectiveness of the proposed model. The model achieves high accuracy of 99%.
