Continuous authentication on smartphone by means of periocular and virtual keystroke

Nowadays, biometric recognition and verification methods are everywhere, trying to face the security issues that constantly affect our digital-every day life. In addition, many special-purpose applications, also need a constant (continuous) verification of the user in order to avoid that a sensitive operation is executed by an impostor; as an example let think to banking operations. In this paper, a continuous authentication method on mobile device is presented, which uses smartphone gestures data for the constant verification of the user and periocular data for a second step verification module. The results executed over two datasets show a verification accuracy of 83% and 94% approximately, respectively for smartphone touch features and periocular data.