In recent years, the rise of artificial intelligence (AI) has led to the generation of vast amounts of content, both real and synthetic. The challenge of distinguishing between AI-generated and real content has become increasingly important, particularly in detecting fake information across various modalities, such as text, images, and videos. This project aims to build a multi-modal fake information detection system that leverages machine learning and deep learning techniques. The system will classify content as either AI-generated or real using specialized algorithms for text (RoBERTa), image (CNN, MobileNet), and video (CNN + GRU). Additionally, Explainable AI (XAI) techniques will be implemented for transparency in text classification. The project will utilize a CSV dataset for text classification, an image dataset for image classification, and a video dataset for analyzing videos. By combining these multiple modalities, the system will enhance the ability to detect fake content more effectively. The user-friendly interface will allow users to upload text, images, and videos, providing a comprehensive approach to fake information detection. This system has applications in areas such as content moderation, media verification, and online security.

Keywords: AI-generated content, fake information detection, multi-modal classification, machine learning, deep learning, text classification, image classification, video classification, XAI, system development.