Deakin University
Browse

Video deepfake detection using Particle Swarm Optimization improved deep neural networks

Download (3.52 MB)
Version 3 2024-06-19, 00:16
Version 2 2024-06-19, 00:07
Version 1 2024-03-13, 00:58
journal contribution
posted on 2024-06-19, 00:16 authored by L Cunha, L Zhang, B Sowan, Chee Peng Lim, Y Kong
AbstractAs complexity and capabilities of Artificial Intelligence technologies increase, so does its potential for misuse. Deepfake videos are an example. They are created with generative models which produce media that replicates the voices and faces of real people. Deepfake videos may be entertaining, but they may also put privacy and security at risk. A criminal may forge a video of a politician or another notable person in order to affect public opinions or deceive others. Approaches for detecting and protecting against these types of forgery must evolve as well as the methods of generation to ensure that proper information is supplied and to mitigate the risks associated with the fast evolution of deepfakes. This research exploits the effectiveness of deepfake detection algorithms with the application of a Particle Swarm Optimization (PSO) variant for hyperparameter selection. Since Convolutional Neural Networks excel in recognizing objects and patterns in visual data while Recurrent Neural Networks are proficient at handling sequential data, in this research, we propose a hybrid EfficientNet-Gated Recurrent Unit (GRU) network as well as EfficientNet-B0-based transfer learning for video forgery classification. A new PSO algorithm is proposed for hyperparameter search, which incorporates composite leaders and reinforcement learning-based search strategy allocation to mitigate premature convergence. To assess whether an image or a video is manipulated, both models are trained on datasets containing deepfake and genuine photographs and videos. The empirical results indicate that the proposed PSO-based EfficientNet-GRU and EfficientNet-B0 networks outperform the counterparts with manual and optimal learning configurations yielded by other search methods for several deepfake datasets.

History

Journal

Neural Computing and Applications

Volume

36

Pagination

8417-8453

Location

Berlin, Germany

Open access

  • Yes

ISSN

0941-0643

eISSN

1433-3058

Language

eng

Publication classification

C1 Refereed article in a scholarly journal

Publisher

Springer

Usage metrics

    Research Publications

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC