Detection of tampered real time videos using deep neural networks

In recent years, there has been a significant increase in the creation and sharing of videos that promote the utilization of digitally interactive multimedia, including music, graphics, and videos, across various devices. This trend encompasses both social networking applications and everyday tasks, mirroring the growing reliance on digital communication devices. Forgery techniques and motivations in the digital realm have undergone significant advancements. Previously, video editing methods were employed to enhance digital content. However, the proliferation of affordable and user-friendly video editing software has introduced several drawbacks and risks associated with these editing techniques. These editing tools can be misused to create misleading, altered, or fabricated videos for malicious purposes, such as spreading misinformation, deception, or defamation. In order to produce altered or fraudulent videos, additional footage is mixed, edited, or synthesized. Sophisticated editing techniques can make it challenging to detect forged videos, making it easier for forgeries to be mistakenly perceived as genuine. Existing method uses methods that detect forgery in videos with simply static backgrounds only. Proposed systems uses a deep learning strategy that incorporates transfer learning utilizing VGG16 and Customized CNN layers to categorize real time videos as tampered or authentic. With the aid of deep neural networks, the suggested method may identify forgery in films with both static and moving backgrounds. The experimental findings show that the suggested strategy is more accurate and effective than existing methods also it provides trustworthy results with low computing cost and strong detection performance.