DeepVision: A Hybrid Deepfake Detection Framework Using Deep Learning Approaches

Abstract

Over the past decade, rapid progress in artificial intelligence (AI), machine learning, and deep learning has introduced sophisticated techniques for multimedia manipulation. Although such technologies have legitimate applications in entertainment and education, malicious actors increasingly exploit them for disinformation campaigns, political propaganda, identity fraud, and targeted harassment. High-quality synthetic videos and images commonly known as deepfakes pose a growing threat to digital security and public trust. This paper introduces DeepVision, a hybrid deepfake detection framework that fuses EfficientNet-B0 with a Vision Transformer (ViTB/16) to exploit both local texture features and global spatial dependencies simultaneously. The EfficientNet-B0 branch extracts fine-grained local texture and manipulation artefacts, while the Vision Transformer captures long range contextual relationships across facial regions using multi-head self-attention. The model is trained on a combined dataset derived from FaceForensics++ (FF++) and the DeepFake Detection Challenge (DFDC), comprising 120,000 labeled face images. Model performance is evaluated using accuracy, precision, recall, F1- score, confusion matrix, and ROC-AUC metrics. Experimental results demonstrate strong classification performance, achieving 98% accuracy and an AUC of 0.9973 on the combined dataset, representing competitive performance relative to recent state-of-the-art studies. The proposed framework supports both image-based and video-based deepfake detection and is suitable for real-world deployment in digital forensics and media authentication applications.