Mobile biometrics are ways of uniquely identifying users based on interactions between their body and mobile device sensors.

As is the case with computer-based behavioral-biometric technologies, mobile behavioral-biometric technologies are able to analyze and identify unique, individual micro-patterns of interaction between a user's body, its habitual environment, and their mobile device.

Identity signals for mobile biometric technologies may include: the way in which users swipe, tap, pinch-zoom, type, or apply pressure to device touchscreens; accelerometer, orientation, and compass sensor data measuring how users carry, hold, and walk with their devices; ambient light sensor and magnetometer data measuring properties about the environments that users frequent; and geolocation data measuring users' typical movements and environments.

In mobile behavioral biometrics, these signals are captured and analyzed by a machine learning engine to enable a comparison between a known user's behavioral-biometric profile and the profile of whomever happens to currently be carrying the device, enabling the user currently carrying the device to be invisibly authenticated—in the background—as the "right" user when these profiles match.