Deep Learning Approaches for Deepfake Detection and Classification in Video Datasets: A Comprehensive Survey

Abstract

The development of deepfakes is becoming a serious threat to multimedia security, therefore making the need for robust and efficient detection systems vital. In this paper, an in-depth review of deep learning approaches that have been developed towards the automatic detection of deepfake videos is carried out. This includes twenty research papers published within the period of 2023 to 2026, discussing deep fake video detectors that use Convolutional Neural Networks (CNN) models, transformer models, graph models, ensemble learning models, and hybrids. Spatial and temporal learning approaches adopted in the detection of facially manipulated videos are discussed. Nonetheless, despite numerous developments, current detection systems are facing challenges like computational complexity, poor generalization, and susceptibility to distortions, among others. Also, the use of a large annotated database further restricts the application. Some of the advancements made recently include vision transformers, graph neural networks, and optimization of ensemble models to enhance performance. The future research needs to concentrate more on lightweight and generalized deep learning models that can be scalable and interpretable. The paper offers a systematic review of recent advancements in deepfake video detection research.