Deepfake Detection with Deep Learning: Convolutional Neural Networks versus Transformers

被引:2
|
作者
Thing, Vrizlynn L. L. [1 ]
机构
[1] Singapore Technol Engn, Singapore, Singapore
关键词
deepfakes; misinformation; detection; deep learning; convolutional neural networks; transformers; authenticity verification;
D O I
10.1109/CSR57506.2023.10225004
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The rapid evolvement of deepfake creation technologies is seriously threating media information trustworthiness. The consequences impacting targeted individuals and institutions can be dire. In this work, we study the evolutions of deep learning architectures, particularly CNNs and Transformers. We identified eight promising deep learning architectures, designed and developed our deepfake detection models and conducted experiments over well-established deepfake datasets. These datasets included the latest second and third generation deepfake datasets. We evaluated the effectiveness of our developed single model detectors in deepfake detection and cross datasets evaluations. We achieved 88.74%, 99.53%, 97.68%, 99.73% and 92.02% accuracy and 99.95%, 100%, 99.88%, 99.99% and 97.61% AUC, in the detection of FF++ 2020, Google DFD, Celeb-DF, Deeper Forensics and DFDC deepfakes, respectively. We also identified and showed the unique strengths of CNNs and Transformers models and analysed the observed relationships among the different deepfake datasets, to aid future developments in this area.
引用
收藏
页码:246 / 253
页数:8
相关论文
共 50 条
  • [31] Learning ability of interpolating deep convolutional neural networks
    Zhou, Tian-Yi
    Huo, Xiaoming
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2024, 68
  • [32] Deep Learning of Graphs with Ngram Convolutional Neural Networks
    Luo, Zhiling
    Liu, Ling
    Yin, Jianwei
    Li, Ying
    Wu, Zhaohui
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2017, 29 (10) : 2125 - 2139
  • [33] LEARNING CONVOLUTIONAL NEURAL NETWORKS WITH DEEP PART EMBEDDINGS
    Gupta, Nitin
    Mujumdar, Shashank
    Agarwal, Prerna
    Jain, Abhinav
    Mehta, Sameep
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 2037 - 2041
  • [34] Deep learning for steganalysis via convolutional neural networks
    Qian, Yinlong
    Dong, Jing
    Wang, Wei
    Tan, Tieniu
    MEDIA WATERMARKING, SECURITY, AND FORENSICS 2015, 2015, 9409
  • [35] Convolutional deep-learning artificial neural networks
    Lutsiv, V. P.
    JOURNAL OF OPTICAL TECHNOLOGY, 2015, 82 (08) : 499 - 508
  • [36] Deep Learning Convolutional Neural Networks for Radio Identification
    Riyaz, Shamnaz
    Sankhe, Kunal
    Ioannidis, Stratis
    Chowdhury, Kaushik
    IEEE COMMUNICATIONS MAGAZINE, 2018, 56 (09) : 146 - 152
  • [37] A primer on deep learning and convolutional neural networks for clinicians
    Iglesias, Lara Lloret
    Bellon, Pablo Sanz
    del Barrio, Amaia Perez
    Fernandez-Miranda, Pablo Menendez
    Gonzalez, David Rodriguez
    Vega, Jose A.
    Mandly, Andres A. Gonzalez
    Blanco, Jose A. Parra
    INSIGHTS INTO IMAGING, 2021, 12 (01)
  • [38] Deep learning electromagnetic inversion with convolutional neural networks
    Puzyrev, Vladimir
    GEOPHYSICAL JOURNAL INTERNATIONAL, 2019, 218 (02) : 817 - 832
  • [39] A primer on deep learning and convolutional neural networks for clinicians
    Lara Lloret Iglesias
    Pablo Sanz Bellón
    Amaia Pérez del Barrio
    Pablo Menéndez Fernández-Miranda
    David Rodríguez González
    José A. Vega
    Andrés A. González Mandly
    José A. Parra Blanco
    Insights into Imaging, 12
  • [40] Hebbian Learning Meets Deep Convolutional Neural Networks
    Amato, Giuseppe
    Carrara, Fabio
    Falchi, Fabrizio
    Gennaro, Claudio
    Lagani, Gabriele
    IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT I, 2019, 11751 : 324 - 334