TheFacebook authorities did not get the expected results by organizing politicalpropaganda, pornography, or aggressive fake videos \'Deepfake DetectionChallenge\' using deep learning technology. This is because the high-performancemodels have been able to detect a maximum of 75.18 percent of Deepfake videoaccurately.

Twothousand people participated in the competition. During this time, theyreceived training and created a new dataset by creating about 35,000 differentmodels. They work with one lakh videos of 3,000 actors and actresses. Amongthem, Selim Seferbekov identified fake videos with an average of 85.18 percent,ranking first, WM second, Enteclab third, Eighteen Years Old fourth and TheMedics fifth.

Ina statement, Facebook authorities said the competition created a baseline foridentifying deepfake videos. This competition will play an important role increating a large number of different data sets and benchmarking dipfeckdetection models, working with new technologies and learning from each other.