Liveness detection methods implementation to face identification reinforcement in gaming services
Vyacheslav Vladimirovich Zolotarev, Alina O. Povazhnyuk, Маро Екатерина Александровна · 2019
Gaming services, including EduTech services, do not use strong user identification and authentication practically. The most serious barrier in terms of information security is biometrics. The problem of replacing the biometric identifier taken from a smartphone or mobile computer camera is considered in the article. Solution of this problem for gaming services is based on the hybrid method called liveness detection. The article describes the requirements and experimental values for enhanced identification. The architecture and parameters of a convolutional neural network that implements the recognition of an additional feature are also shown. The order and results of testing the enhanced identification module are given. The developed identification module has the an additional feature recognition accuracy up to 100% in situation that user's head is turned up to 30°, and up to 70% when the user's head is turned up to 45°. The FAR value of this system was 1%. The FRR value was 0%. The module does not use additional hardware and can be used on a smartphone or mobile computer without upgrading the latter. Attack with the substitution of a biometric feature supplied from the camera is much more difficult to be realized if suggested solution is implemented.