Detecting Deepfakes with Deep Learning and Gabor  Filters

Wildan J. Jameel; Suhad M.  Kadhem; Ayad R. Abbas

doi:10.14500/aro.10917

Wildan J. Jameel Department of Computer Science, College of Science for Women, University of Baghdad, Baghdad, Iraq https://orcid.org/0000-0002-1185-0428
Suhad M. Kadhem Department of Computer Science, University of Technology, Baghdad, Iraq https://orcid.org/0000-0003-0471-8231
Ayad R. Abbas Department of Computer Science, University of Technology, Baghdad, Iraq https://orcid.org/0000-0002-9797-421X

Keywords: Deepfake detection, deep learning, Gabor filter, VGG16

Abstract

The proliferation of many editing programs based on artificial intelligence techniques has contributed to the emergence of deepfake technology. Deepfakes are committed to fabricating and falsifying facts by making a person do actions or say words that he never did or said. So that developing an algorithm for deepfakes detection is very important to discriminate real from fake media. Convolutional neural networks (CNNs) are among the most complex classifiers, but choosing the nature of the data fed to these networks is extremely important. For this reason, we capture fine texture details of input data frames using 16 Gabor filters in
different directions and then feed them to a binary CNN classifier instead of using the red-green-blue color information. The purpose of this paper is to give the reader a deeper view of (1) enhancing the efficiency of distinguishing fake facial images from real facial images by developing a novel model based on deep learning and Gabor filters and (2) how deep learning (CNN) if combined with forensic tools (Gabor filters) contributed to the detection of deepfakes. Our experiment shows that the training accuracy reaches about 98.06% and 97.50% validation. Likened to the state-of-the-art methods, the proposed model has higher efficiency.

Downloads

Download data is not yet available.

Author Biographies

Wildan J. Jameel, Department of Computer Science, College of Science for Women, University of Baghdad, Baghdad, Iraq

Wildan J. Hadi is a lecturer working at the department of computer science, College of Science for Women, University of Bghdad, Iraq. She got her B.Sc. degree in computer science from University of Baghdad,in 2006, and her M.Sc. degree in Computer Science from the University of Technology, in 2008. Her research interests are in Image Processing, Video Analysis, Deep Learning, Face Detection.

Suhad M. Kadhem, Department of Computer Science, University of Technology, Baghdad, Iraq

Suhad M. Kadhem is an Assistant Prof. working at the department of Computer Science, University of Technology, Bagdad, Iraq. She got her B.Sc., M.Sc and Ph.D.degrees in Computer Science from the University of Technology, Her research interests are in artificial intelligence, natural language processing (especially Arabic language processing), and computer security (especially steganography).

Ayad R. Abbas, Department of Computer Science, University of Technology, Baghdad, Iraq

Ayad R. Abbas is an Assistant Prof. working at the department of Computer Science, University of Technology, Baghdad, iraq. He got B.Sc. degree in computer science, University of Technology in 2003, also got a B.Sc. degree in Chemical Engineering, University of Baghdad, in 1999. He got his M.Sc. degree in Computer Science from the University of Technology, in 2005, and the Ph.D. degree in Artificial Intelligent, from Wuhan University, China, in 2009. His research interests are in Artificial Intelligent, Machine learning, Natural Language Processing, Deep Learning, Data mining, Web mining, Information retrieval, Soft Computing, E-learning, E-Commerce, Recommended System.

References

Abdul, Z.K., 2019. Kurdish speaker identification based on one dimensional convolutional neural network. Computational Methods for Differential Equations, 7, pp.566-572.

Afchar, D., Nozick, V., Yamagishi, J. and Echizen, I., 2018 Mesonet: A compact facial video forgery detection network. In: 2018 IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, pp.1-7.

Al-Talabani, A.K., 2020. Automatic recognition of arabic poetry meter from speech signal using long short-term memory and support vector machine. ARO-The Scientific Journal of Koya University, 8(1), pp.50-54.

Battiato, S. and Messina, G., 2009. Digital forgery estimation into DCT domain: A critical analysis. In: Proceedings of the First ACM Workshop on Multimedia in Forensics, pp.37-42.

Dang, H., Liu, F., Stehouwer, J., Liu, X. and Jain, A.K., 2020. On the Detection of Digital Face Manipulation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition, pp.5781-5790.

Dora, L., Agrawal, S., Panda, R. and Abraham, A., 2017. An evolutionary single Gabor kernel based filter approach to face recognition. Engineering Applications of Artificial Intelligence, 62, pp.286-301.

Dufour, N., (2019) ‘Deepfakes Detection Dataset’. Fu, H. and Cao, X., 2012. Forgery authentication in extreme wide-angle lens using distortion cue and fake saliency map. IEEE Transactions on Information Forensics and Security, 7(4), pp.1301-1314.

Ghafoor, K.J., Rawf, K.M.M., Abdulrahman,A.O., Taher, S.H., 2021. Kurdish dialect recognition using 1D CNN. ARO-The Scientific Journal of Koya University, 9(2), pp.10-14.

Güera, D. and Delp, E.J., 2018. Deepfake video detection using recurrent neural networks. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, pp.1-6.

Johnson, D., 2021. What is a Deepfake? Everything you need to Know. Available from: https://www.businessinsider.com/what-is-deepfake [Last accessed on 2021 Sep 07].

Karras, T., Laine, S. and Aila, T., 2019. A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.4401-4410.

Lim, H., 2021. The Best (and worst) Deepfakes Developments in 2020, Lionbridge AI. Available from: https://lionbridge.ai/articles/a-look-at-deepfakesin-2020 [Last accessed on 2020 Apr 24].

Mao, X. and Li, Q., 2021. Generative Adversarial Networks for Image Generation. Springer Nature. Available from: https://t.ly/9dL7.

Montserrat, D.M., Hao, H., Yarlagadda, S.K., Baireddy, S., Shao, R., Horvath, J., Bartusiak, E., Yang, J., Guera, D., Zhu, F. and Delp, E.J., 2020. Deepfakes detection with automatic face weighting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.668-669.

Moran, T.B., 2021, What is a deep Fake and how are they made? Available from: https://www.smh.com.au/technology/what-is-the-difference-between-afake-and-a-deepfake-20200729-p55ghi.html [Last accessed on 2021 Nov 30].

Mullan, P., Cozzolino, D., Verdoliva, L. and Riess., C, 2017. Residual-based forensic comparison of video sequences. In: 2017 IEEE International Conference on Image Processing (ICIP). IEEE, pp.1507-1511.

Nguyen, H.H., Yamagishi, J. and Echizen, I., 2019. Capsule-forensics: Using capsule networks to detect forged images and videos. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp.2307-2311.

Puglisi, G., Bruna, A.R., Galvan, F. and Battiato, S., 2013. First JPEG quantization matrix estimation based on histogram analysis. In: 2013 IEEE International Conference on Image Processing. IEEE, pp.4502-4506.

Simonyan, K. and Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv, 2014, p.14091556.

Sudiatmika, I.B.K. and Rahman, F., 2019. Image forgery detection using error level analysis and deep learning. Telkomnika, 17(2), pp.653-659.

Wang, X., Li, W., Mu, G., Huang, D. and Wang, Y., 2018. Facial expression synthesis by u-net conditional generative adversarial networks. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp.283-290.

Yang, J., Li, A., Xiao, S., Lu, W. and Gao, X., 2021. MTD-net: Learning to detect deepfakes images by multi-scale texture difference. IEEE Transactions on Information Forensics and Security, 16, pp.4234-4245.

Yu, Y., Gong, Z., Zhong, P. and Shan, J., 2017. Unsupervised representation learning with deep convolutional neural network for remote sensing images. In: International Conference on Image and Graphics. Springer, Berlin. pp.97-108.

Zhou, Y. and Shi, B.E., 2017. Photorealistic facial expression synthesis by the conditional difference adversarial autoencoder. In: 2017 7th International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE, pp.370-376.

Zhu, H., Zhou, Q., Zhang, J. and Wang, J.Z., 2018. Facial aging and rejuvenation by conditional multi-adversarial autoencoder with ordinal regression. arXiv, 2018, p.180402740.