StrokePIN

Keystroke dynamics-based authentication is a promising approach to enhance the security of personal identiffcation number (PIN)-based authentication systems for mobile devices. To support research, we design a set of experiments and collect a new multi-modality dataset of PIN keystroke dynamics from 97 users comprising 18,935 unique entries. Our dataset captures users' input patterns under two behavioral states: walking and sitting. It consists of two complementary sub-databases: a Motion Sensor Database and a Touch Database, each recording specific dimensions of user interaction. The data of touch sensors are recorded at a maximum rate of 120 Hz. The sensor sampling rate is configured to SensorManager.SENSOR_DELAY_NORMAL, where the sampling frequency is 5 Hz.