AI Based Fake Images and Videos Detection Using Deep Learning Model
The rapid growth of artificial intelligence has led to the development of advanced technologies capable of generating highly realistic fake images and videos, commonly known as deepfakes. Although these technologies have useful applications in entertainment, education, and digital media, they can also be misused for spreading misinformation, identity theft, fraud, and other cybercrimes. This paper presents an AI-based fake image and video detection system using deep learning models such as InceptionV3, EfficientNet, and a Hybrid model. The proposed system preprocesses input images and video frames through resizing, normalization, and data augmentation to improve model performance. The trained models extract meaningful visual features and classify the uploaded media as real or fake. The Hybrid model combines the strengths of InceptionV3 and EfficientNet to achieve improved feature extraction and higher classification accuracy. The performance of the proposed system is evaluated using standard metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that the Hybrid model outperforms the individual models in detecting manipulated media. The proposed approach provides an efficient, accurate, and reliable solution for identifying AI-generated content and helps improve the authenticity, security, and trustworthiness of digital media across various online platforms.