DEEPFAKE DETECTION TECHNIQUES: A REVIEW


EOI: 10.11242/viva-tech.01.04.002

Download Full Text here



Citation

Mr. Neeraj Guhagarkar, Ms. Sanjana Desai, Mr. Swanand Vaishampayan, Prof. Ashwini Save, "DEEPFAKE DETECTION TECHNIQUES: A REVIEW", VIVA-IJRI Volume 1, Issue 4, Article 2, pp. 1-10, 2021. Published by Computer Engineering Department, VIVA Institute of Technology, Virar, India.

Abstract

Noteworthy advancements in the field of deep learning have led to the rise of highly realistic AI generated fake videos, these videos are commonly known as Deepfakes. They refer to manipulated videos, that are generated by sophisticated AI, that yield formed videos and tones that seem to be original. Although this technology has numerous beneficial applications, there are also significant concerns about the disadvantages of the same. So there is a need to develop a system that would detect and mitigate the negative impact of these AI generated videos on society. The videos that get transferred through social media are of low quality, so the detection of such videos becomes difficult. Many researchers in the past have done analysis on Deepfake detection which were based on Machine Learning, Support Vector Machine and Deep Learning based techniques such as Convolution Neural Network with or without LSTM .This paper analyses various techniques that are used by several researchers to detect Deepfake videos.

Keywords

Convolutional Neural Networks, Deepfake Detection, Long Short Term Memory , Super Resolution, Facial Forgery.

References

  1. Xin Yang, Yeuzen Li and Siwei Lyu, “EXPOSING DEEP FAKES USING INCONSISTENT HEAD POSES”, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
  2. Rohita Jagdale and Sanjeevani Shah, “A Novel Algorithm for Video Super-Resolution”, Proceedings of ICTIS 2018, Volume 1, Information and Communication Technology for Intelligent Systems (pp.533-544).
  3. Siwei Lyu,”DEEPFAKE DETECTION: CURRENT CHALLENGES AND NEXT STEPS”,2020 IEEE International Conference on Multimedia & Expo Workshops(ICMEW).
  4. Digvijay Yadav, Sakina Salmani, “Deepfake: A Survey on Facial Forgery Technique Using Generative Adversarial Network”, Proceedings of the International Conference on Intelligent Computing and Control Systems (ICICCS 2019).IEEE Xplore Part Number: CFP19K34-ART; ISBN: 978-1-5386-8113-8.
  5. Irene Amerini, Leonardo Galteri, Roberto Caldelli, Alberto Del Bimbo, “Deepfake Video Detection through Optical Flow based CNN”, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).
  6. Peng Chen, Jin Liu, Tao Liang, Guangzhi Zhou, Hongchao Gao, Jiao Dai1, Jizhong Han, “FSSPOTTER: SPOTTING FACE-SWAPPED VIDEO BY SPATIAL AND TEMPORAL CLUES”, 2020 IEEE International Conference on Multimedia and Expo (ICME).
  7. Mohammed A. Younus, Taha M. Hasan, “Abbreviated View of Deepfake Videos Detection Techniques”, 2020 6th International Engineering Conference “Sustainable Technology and Development" (IEC).
  8. Shivangi Aneja, Matthias Nießner, “Generalized Zero and Few-Shot Transfer for Facial Forgery Detection”, arXiv:2006.11863v1 [cs.CV] 2020.
  9. Xin Tao, Hongyun Gao, Renjie Liao, Jue Wang, Jiaya Jia, “Detail-revealing Deep Video Super-resolution”, 2017 IEEE International Conference on Computer Vision (ICCV)
  10. Jin Yamanaka, Shigesumi Kuwashima , and Takio Kurita ,“Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network”, (2017 Springer).
  11. David Guera, Edward J. Delp, “Deepfake Video Detection Using Recurrent Neural Networks”, 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).
  12. Mousa Tayseer Jafar, Mohammad Ababneh, Mohammad Al-Zoube, Ammar Elhassan,“Digital Forensics and Analysis of Deepfake Videos”,(IEEE 2020).
  13. Ranjan, Sarvesh Patil, Faruk Kazi,“Improved Generalizability of Deep-Fakes Detection Using Transfer Learning Based CNN Framework”,(IEEE 2020).
  14. Mingzhu Luo, Yewei Xiao, Yan Zhou,“ Multi-scale face detection based on convolutional neural network”,IEEE 2018.
  15. Jiangang Yu and Bir Bhanu,“Super-resolution of Facial Images in Video with Expression Changes”,IEEE 5th Conference on Advanced Video and Signal based Surveillance,2018.
  16. Yuqian Zhou, Ding Liu, Thomas Huang ,“Survey of Face Detection on Low-quality Images”,2018 13th IEEE International Conference on Automatic Face and Gesture Recognition.
  17. Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies,Matthias Nießner, “ FaceForensics++: Learning to Detect Manipulated Facial Images”Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV),2019, pp. 1-11.
  18. Falko Matern ,Christian Riess , Marc Stamminger, Friedrich-Alexander ,“Exploiting Visual Artifacts to Expose Deep Fakes and Face”,2019 IEEE Winter Application of Computer Vision Workshop.
  19. Scott McCloskey and Michael Albright,“DETECTING GAN-GENERATED IMAGERY USING SATURATION CUES”, 2019 IEEE.
  20. Atra Akandeh and Fathi M. Salem,“Slim LSTM NETWORKS: LSTM 6 and LSTM C6”,2019 IEEE.
  21. Chao Dong, Chen Change Loy, Member, IEEE, Kaiming He, Member, IEEE, and Xia oou Tang, Fellow,“Image Super-Resolution Using Deep Convolutional Networks”,IEEE Transaction on Pattern Analysis and Machine Intelligence(2016).
  22. Faten F Kharbat, Tarik Elamsy, Ahmed Mahmoud, Rami ,“Image Feature Detectors for Deepfake Video Detection”,IEEE 2019.
  23. Chuan-Chuan Low, Lee-Yeng Ong, Voon-Chet Koo,“Experimental Study on Multiple Face Detection with Depth and Skin Colour”,IEEE 2019.
  24. Badhrinarayan Malolan, Ankit Parekh, Faruk Kazi ,“Explainable Deep-Fake Detection Using Visual Interpretability Methods”,2020 3rd International conference on Information and Computer Technologies(ICICT).
  25. https://www.indiatoday.in/india-today-insight/story/india-s-deepfake-problem-videos-are-neither-deep-n or-fake-1643883-2020-02-06 (last accessed on 21 October 2020)