CI Fakegaurd :Deep Learning For Real Vs AI Generated ImageDetection

Abstract

The rapid advancement of generative models has led to the widespread creation of highly realistic AI- generated images, raising serious concerns about misinformation, digital forgery, and identity misuse. The project titled “CI FakeGuard: Deep Learning for Real vs AI-Generated Image Detection” presents an intelligent detection framework designed to distinguish authentic images from synthetically generated ones. The system leverages advanced deep learning architectures, particularly Convolutional Neural Networks (CNNs), to extract subtle spatial, frequency, and texture-based features that differentiate real images from AI-generated content. The model is trained on a diverse dataset containing both real-world photographs and images produced by modern generative techniques such as GANs and diffusion models. Performance is evaluated using accuracy, precision, recall, and F1-score metrics to ensure robust detection capability. CI FakeGuard aims to enhance digital trust, strengthen cybersecurity measures, and provide an automated solution for identifying manipulated or artificially created visual content across various online platforms