Video Deepfake classification using particle swarm optimization-based evolving ensemble models

Li Zhang, Dezong Zhao, Chee Peng Lim, Houshyar Asadi, Haoqian Huang, Yonghong Yu, Rong Gao

Abstract: Highlights•We propose evolving ensembles of 3D CNNs and CNN-RNNs for video deepfake detection.•A PSO algorithm is proposed to optimize hyper-parameters and formulate ensembles.•It synthesizes elite signals and selects optimal search actions using Q-learning.•Numerical analysis-based swarm leader enhancement is also exploited.•Our system depicts a superior capability in video forgery classification.