Ms.Bismi Fathima Nasar, Ms.Sajini. T , Ms.Elizabeth Rose Lalson , ,
Affiliations 1: Computer Science and Engineering, ER & DCI Institute of Technology, KTU, Thiruvananthapuram, India , 2: Knowledge Resource Centre, CDAC, Thiruvananthapuram, India; 3 : Computer Science and Engineering, ER & DCI Institute of Technology, KTU, Thiruvananthapuram, India
With the recent advancement in the Deep Learning algorithm, its application has been broadened over various fields ranging from big data analytics to human biometric systems. One such field where it takes up the hand is the implementation of various application like FaceApp, FakeApp etc. that is used in the generation of manipulated media files which is termed as Deepfake. These application has a wider increase in its popularity among common public due to its user friendly features and are used in various domains like Digital Fraud, Cyber Crimes, Politics and in even in Military Activities. So, it is very much important to develop some kind of detection techniques that can take away this kind of forgeries and put up a new step in video and audio forensics. In this paper, we present the various creation and detection techniques that is up now in research in Deepfake using various techniques like Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short Term Memory (LSTM) etc. and thus provide a backbone in the implementation of a new scheme that would be more compactable and accurate in the detection of Deepfakes. Also we done a comparison study on various techniques under traditional and state of the art approach and brought up a conclusion that most of the techniques under traditional approach are time consuming process, need expertise knowledge over the technology for the user to use them etc. where as in the case of state of the art approach, the techniques require less time for processing and anyone with less knowledge over the technology can use this technologies for the creation and detection of Deepfake.
Ms.Bismi Fathima Nasar,Ms.Sajini. T,Ms.Elizabeth Rose Lalson."A Survey on Deepfake Detection Techniques". International Journal of Computer Engineering In Research Trends (IJCERT) , ISSN:2349-7084, Vol.7, Issue 08,pp.49-55, August- 2020, URL:https://ijcert.org/ems/ijcert_papers/V7I808.pdf,
Keywords : Recurrent Neural Network, Long Short Term Memory, Convolutional Neural Network, Deepfake
 Raahat Devender Singh, Naveen Aggarwal,” Video content authentication techniques: a comprehensive survey”, Springer, Multimedia Systems, pp. 211- 240, 2018.
 David G’uera Edward J. Delp,” Deepfake Video Detection Using Recurrent Neural Networks”, Video and Image Processing Laboratory (VIPER), Purdue University,2018.
 Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal, Wael AbdAlmageed, Iacopo Masi, Prem Natarajan,” Recurrent Convolutional Strategies for Face Manipulation Detection in Videos”, In proceeding of the IEEE Xplore Final Publication, pp. 80-87, 2018.
 Xinyi Ding, Zohreh Razieiy, Eric C, Larson, Eli V, Olinick, Paul Krueger, Michael Hahsler,” Swapped Face Detection using Deep Learning and Subjective Assessment”, Research Gate, pp. 1-9, 2019.
 Peng Zhou, Xintong Han, Vlad I. Morariu Larry S. Davis,” Two-Stream Neural Networks for Tampered Face Detection”, IEEE Conference on Computer Vision and Pattern Recognition, 2019
 Chih-Chung Hsu, Yi-Xiu Zhuang, and Chia-Yen Lee,” Deep Fake Image Detection based on Pairwise Learning”, MDPI, Applied Science,2020, doi:10.3390/app10010370.
 Fang Liu, Licheng Jiao, Fellow, IEEE, and Xu Tang, Member” Task- Oriented GAN for PolSAR Image Classification and Clustering”, IEEE Transactions On Neural Networks and Learning Systems, Volume 30, Issue 9, 2019.
 Jawadul H. Bappy, Cody Simons, Lakshmanan Nataraj, B.S. Manjunath, and Amit K. Roy-Chowdhury,” Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries”, IEEE Transaction on Image Processing, Volume: 28 , Issue: 7 ,pp. 1-14, 2019.
 Xinsheng Xuan, Bo Peng, Wei Wang and Jing Dong,” On the Generalization of GAN Image Forensics”, Computer Vision and Pattern Recognition, Cornell University, Volume 1, pp. 1-8, 2019.
 Yuezun Li, Siwei Lyu,” Exposing DeepFake Videos by Detecting Face Warping Artifacts”, In Proceedings of the IEEE Xplore Final Publication, pp. 46- 52, 2019.
 Pavel Korshunov, S´ebastien Marcel,” Speaker Inconsistency Detection in Tampered Video”, 26th European Signal Processing Conference (EUSIPCO), 2018, ISBN 978-90-827970-1-5.
 Huy H. Nguyen, Junichi Yamagishi, and Isao Echizen,” Capsule- Forensics: Using Capsule Networks to detect Forged Images and Videos”, ICASSP, pp. 2307 – 2311, 2019
 Li, Y., Chang, M. C., and Lyu, S, “Exposing AI created fake videos by detecting eye blinking”, In IEEE International Workshop on Information Forensics and Security (WIFS) (pp. 1-7). 2018.
 Steven Fernandes, Sunny Raj, Rickard Ewetz, Jodh Singh Pannu, Sumit Kumar Jha, Eddy Ortiz, Iustina Vintila, Margaret Salte,” Detecting deepfake videos using attribution-based confidence metric”, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 308-309), 2020.
 A.M. Rodriguez, Z. Geradts,” Detection of Deepfake Video Manipulation”, In Proceedings of the 20th Irish Machine Vision and Image Processing conference, Belfast, Northern Ireland, pp. 133-136, 2018, ISBN 978-0-9934207-3-3.
 Rohini Sawant and Manoj Sabnis,” A Review of Video Forgery and Its Detection”, IOSR Journal of Computer Engineering (IOSR-JCE) e- ISSN: 2278-0661, Volume 20, Issue 2, p-ISSN: 2278-8727, 2018.
 Thanh Thi Nguyen, Cuong M. Nguyen, Dung Tien Nguyen, Duc Thanh Nguyen and Saeid Nahavandi,” Deep Learning for Deepfakes Creation and Detection”, IEEE, pp. 1-12, 2019.
IJCERT is peer-reviewed scientific Research journal to endorse conservation. We have not put up a paywall to readers, But running a monthly journal costs is a lot. IJCERT has been changed the publication policy from Free publication to pay because of increasing the maintenance cost and other editorial charges. The understanding and cooperation of the author are highly solicited.we still need support to keep the journal flourishing. If our readers help fund it, our future will be more secure.