Unmasking deepfakes based on deep learning and noise residuals
Joint Authors
Abbas, Iyad R.
Hadi, Wildan J.
Kazim, Suhad M.
Source
Iraqi Journal of Computer, Communications and Control Engineering
Issue
Vol. 22, Issue 3 (30 Sep. 2022), pp.111-117, 7 p.
Publisher
Publication Date
2022-09-30
Country of Publication
Iraq
No. of Pages
7
Main Subjects
Information Technology and Computer Science
Abstract EN
The main reason for the emergence of a deepfake (deep learning and fake) term is the evolution in artificial intelligence techniques, especially deep learning.
Deep learning algorithms, which auto-solve problems when giving large sets of data, are used to swap faces in digital media to create fake media with a realistic appearance.
To increase the accuracy of distinguishing a real video from fake one, a new model has been developed based on deep learning and noise residuals.
By using Steganalysis Rich Model (SRM) filters, we can gather a low-level noise map that is used as input to a light Convolution neural network (CNN) to classify a real face from fake one.
The results of our work show that the training accuracy of the CNN model can be significantly enhanced by using noise residuals instead of RGB pixels.
Compared to alternative methods, the advantages of our method include higher detection accuracy, lowest training time, a fewer number of layers and parameters.
American Psychological Association (APA)
Hadi, Wildan J.& Kazim, Suhad M.& Abbas, Iyad R.. 2022. Unmasking deepfakes based on deep learning and noise residuals. Iraqi Journal of Computer, Communications and Control Engineering،Vol. 22, no. 3, pp.111-117.
https://search.emarefa.net/detail/BIM-1492790
Modern Language Association (MLA)
Hadi, Wildan J.…[et al.]. Unmasking deepfakes based on deep learning and noise residuals. Iraqi Journal of Computer, Communications and Control Engineering Vol. 22, no. 3 (Sep. 2022), pp.111-117.
https://search.emarefa.net/detail/BIM-1492790
American Medical Association (AMA)
Hadi, Wildan J.& Kazim, Suhad M.& Abbas, Iyad R.. Unmasking deepfakes based on deep learning and noise residuals. Iraqi Journal of Computer, Communications and Control Engineering. 2022. Vol. 22, no. 3, pp.111-117.
https://search.emarefa.net/detail/BIM-1492790
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 116-117
Record ID
BIM-1492790