Hybrid Deep Learning Framework for Social Media Image Forgery Detection

Abstract

The rapid growth of social media has made image sharing a common part of daily communication, but it has also increased the spread of manipulated and misleading images. Fake images can influence public opinion, damage reputations, and contribute to the circulation of false information. This study presents a Hybrid Deep Learning Framework for Social Media Image Forgery Detection, designed to automatically identify forged and authentic images using deep learning techniques. The proposed framework employs a Convolutional Neural Network (CNN) to learn visual patterns and distinguish manipulated images from genuine ones. Before training, the image dataset undergoes preprocessing steps such as resizing, normalization, and data augmentation to improve model performance and generalization. The trained model is evaluated using standard performance measures, including accuracy, precision, recall, and F1-score, to ensure reliable classification. A user-friendly web application is also developed to allow users to upload images and receive instant authenticity predictions. The proposed framework provides an effective solution for detecting fake images on social media, supporting digital content verification, reducing misinformation, and helping users make informed decisions regarding the credibility of shared visual information.