The Deepfake Challenges and Deepfake Video Detection
Worku Muluye Wubet

Worku Muluye Wubet, Lecturer at Wolkite University, Wolkite Ethiopia.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 25, 2020. | Manuscript published on April 10, 2020. | PP: 789-796 | Volume-9 Issue-6, April 2020. | Retrieval Number: E2779039520/2020©BEIESP | DOI: 10.35940/ijitee.E2779.049620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Deep fake is a combination of fake and deep learning technology. Deep learning is the function of artificial intelligence that can be used to create and detect deep fakes. Deep fakes are created using generative adversarial networks, in which two machine learning models exit. One model trains on a dataset and then creates the deep fakes, and the other model tries to detect the deep fakes. The forger creates deep fakes until the other model can’t detect the deep fakes. Deep fakes creating fake videos, images, news, and terrorist events. When deep fake videos, and images increase on social media people will ignore to trust the truth. Deep fakes are increasingly affecting individuals, communities, organizations, security, religions, and democracy. This paper aims to investigate deep fake challenges, and to detect deep fake videos by using eye blinking. Deep fake detections are methods to detect real or deep fake images and videos on social media. Deep fake detection techniques are needed original and fake images or video datasets to train the detection models. In this study, first discussed deep fake technology and its challenges, then identified available video datasets. Following, convolutional neural networks to classify the eye states and long short term memory for sequence learning has been used. Furthermore, the eye aspect ratio was used to calculate the height and width of open and closed eyes and to detect the blinking intervals. The model trained on UADFV dataset to detect fake and real video by using eye blinking and detects 18.4 eye blinks per minute on the real videos and 4.28 eye blinks per minute on fake videos. The overall detection accuracy on real and fake videos was 93.23% and 98.30% respectively. In the future research and development needs more scalable, accurate, reliable and cross-platform deep fake detection techniques. 
Keywords: Deep fake, Deep Fake Detection, Deep Learning, Detection Techniques, Eye Blinking.
Scope of the Article: Software Engineering Techniques and Production Perspectives.