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

被引:3
|
作者
Zhang, Li [1 ]
Zhao, Dezong [2 ]
Lim, Chee Peng [3 ]
Asadi, Houshyar [3 ]
Huang, Haoqian [4 ]
Yu, Yonghong [5 ]
Gao, Rong [6 ]
机构
[1] Univ London, Dept Comp Sci, Royal Holloway, London TW20 0EX, Surrey, England
[2] Univ Glasgow, James Watt Sch Engn, Glasgow City G12 8QQ, Scotland
[3] Deakin Univ, Inst Intelligent Syst Res & Innovat, Geelong, Vic 3216, Australia
[4] Hohai Univ, Coll Energy & Elect Engn, Nanjing 210098, Peoples R China
[5] Nanjing Univ Posts & Telecommun, Coll Tongda, Nanjing 210023, Peoples R China
[6] Hubei Univ Technol, Sch Comp Sci, Wuhan 430068, Peoples R China
关键词
Video deepfake classification; Hybrid deep neural network; 3d convolutional neural network; Evolutionary algorithm; Evolving ensemble classifier; FIREFLY ALGORITHM; ARCHITECTURES; REGRESSION; NETWORKS; IMAGES;
D O I
10.1016/j.knosys.2024.111461
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The recent breakthrough of deep learning based generative models has led to the escalated generation of photorealistic synthetic videos with significant visual quality. Automated reliable detection of such forged videos requires the extraction of fine-grained discriminative spatial-temporal cues. To tackle such challenges, we propose weighted and evolving ensemble models comprising 3D Convolutional Neural Networks (CNNs) and CNNRecurrent Neural Networks (RNNs) with Particle Swarm Optimization (PSO) based network topology and hyperparameter optimization for video authenticity classification. A new PSO algorithm is proposed, which embeds Muller's method and fixed-point iteration based leader enhancement, reinforcement learning-based optimal search action selection, a petal spiral simulated search mechanism, and cross-breed elite signal generation based on adaptive geometric surfaces. The PSO variant optimizes the RNN topologies in CNN-RNN, as well as key learning configurations of 3D CNNs, with the attempt to extract effective discriminative spatial-temporal cues. Both weighted and evolving ensemble strategies are used for ensemble formulation with aforementioned optimized networks as base classifiers. In particular, the proposed PSO algorithm is used to identify optimal subsets of optimized base networks for dynamic ensemble generation to balance between ensemble complexity and performance. Evaluated using several well-known synthetic video datasets, our approach outperforms existing studies and various ensemble models devised by other search methods with statistical significance for video authenticity classification. The proposed PSO model also illustrates statistical superiority over a number of search methods for solving optimization problems pertaining to a variety of artificial landscapes with diverse geometrical layouts.
引用
收藏
页数:40
相关论文
共 50 条
  • [1] Sound classification using evolving ensemble models and Particle Swarm Optimization
    Zhang, Li
    Lim, Chee Peng
    Yu, Yonghong
    Jiang, Ming
    [J]. APPLIED SOFT COMPUTING, 2022, 116
  • [2] Evolving Ensemble Models for Image Segmentation Using Enhanced Particle Swarm Optimization
    Tan, Teck Yan
    Zhang, Li
    Lim, Chee Peng
    Fielding, Ben
    Yu, Yonghong
    Anderson, Emma
    [J]. IEEE ACCESS, 2019, 7 : 34004 - 34019
  • [3] Intelligent optic disc segmentation using improved particle swarm optimization and evolving ensemble models
    Zhang, Li
    Lim, Chee Peng
    [J]. APPLIED SOFT COMPUTING, 2020, 92
  • [4] Particle swarm optimization-based ensemble learning for software change prediction
    Malhotra, Ruchika
    Khanna, Megha
    [J]. INFORMATION AND SOFTWARE TECHNOLOGY, 2018, 102 : 65 - 84
  • [5] Particle swarm optimization-based feature selection in sentiment classification
    Shang, Lin
    Zhou, Zhe
    Liu, Xing
    [J]. SOFT COMPUTING, 2016, 20 (10) : 3821 - 3834
  • [6] Particle swarm optimization-based feature selection in sentiment classification
    Lin Shang
    Zhe Zhou
    Xing Liu
    [J]. Soft Computing, 2016, 20 : 3821 - 3834
  • [7] Video deepfake detection using Particle Swarm Optimization improved deep neural networks
    Leandro Cunha
    Li Zhang
    Bilal Sowan
    Chee Peng Lim
    Yinghui Kong
    [J]. Neural Computing and Applications, 2024, 36 : 8417 - 8453
  • [8] Video deepfake detection using Particle Swarm Optimization improved deep neural networks
    Cunha, Leandro
    Zhang, Li
    Lim, Chee Peng
    Sowan, Bilal
    Kong, Yinghui
    [J]. NEURAL COMPUTING & APPLICATIONS, 2024, 36 (15): : 8417 - 8453
  • [9] A Particle Swarm Optimization-Based Flexible Convolutional Autoencoder for Image Classification
    Sun, Yanan
    Xue, Bing
    Zhang, Mengjie
    Yen, Gary G.
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (08) : 2295 - 2309
  • [10] PARTICLE SWARM OPTIMIZATION-BASED DIMENSIONALITY REDUCTION FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Yang, He
    Du, Qian
    [J]. 2011 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2011, : 2357 - 2360