Opportunistically collecting sensor data from a mobile device to facilitate user identification

1. A method for authenticating and/or identifying a user of a portable electronic device, comprising:

in response to a trigger event, collecting sensor data from one or more sensors in the portable electronic device, wherein the sensor data includes movement-related sensor data caused by movement of the portable electronic device while the portable electronic device is in control of the user;

extracting a feature vector from the sensor data;

analyzing the feature vector using a model trained with sensor data previously obtained from the portable electronic device while the user was in control of the portable electronic device;

generating an associated security score for each of multiple authorized users of the device, based on said analysis of the feature vector; and

identifying the user based on the security scores;

wherein the trigger event comprises an adaptive notification sent at a variable interval determined based on feedback generated by a learner that processes the collected sensor data.

2. The method of claim 1 ,

wherein the movement-related sensor data includes accelerometer data gathered while the user is walking; and

wherein the accelerometer data reflects a characteristic gait of the user while walking.

3. The method of claim 1 , wherein the trigger event comprises a silent push notification received by the portable electronic device.

4. The method of claim 1 , wherein the trigger event comprises a notification received by the portable electronic device from a wireless beacon.

5. The method of claim 1 , wherein the trigger event comprises a periodic notification, which is sent at a predefined interval.

6. The method of claim 1 , wherein:

the feedback relates to one or more of the following:

a change in confidence level for the identity of the user;

a battery level for the portable electronic device;

a usage pattern for the portable electronic device; and

a received notification associated with the portable electronic device.

7. The method of claim 1 , wherein the trigger event comprises a detected activity of the user determined from the collected sensor data.

8. The method of claim 1 , wherein the trigger event comprises a notification that the portable electronic device has entered or exited a predefined region associated with a geofence.

9. The method of claim 1 , wherein the trigger event comprises one or more of the following:

a change in lighting;

a change in sound;

a change in magnetic field;

a detected keyword;

a detected near field communication (NFC) signal;

a received message notification;

a received telephone call;

a user-interaction event associated with the portable electronic device;

an interaction event between the portable electronic device and an external device/sensor;

a screen-on event;

a screen-off event;

a device-unlock event;

a device-unlock failure;

an application-opening event;

a switching-to-an-application event;

a switching cell towers event;

an install-application event;

an uninstall-application event;

a change in a device setting;

a screen brightness adjustment; and

a photograph-taking event.

10. The method of claim 1 , wherein the one or more sensors include one or more of the following:

an accelerometer;

a touchscreen;

a gyroscope;

an inertial sensor;

an ambient light sensor;

an image sensor;

a camera;

an odor sensor;

a temperature sensor;

a barometric-pressure sensor;

a cellular radio signal strength sensor;

a Bluetooth radio signal strength sensor;

a near-field communication (NFC) sensor;

a network-proximity sensor;

an infrared sensor;

a magnetometer;

a battery sensor;

a force-touch measurement sensor;

a multi-touch measurement sensor;

a sensor in a mouse;

a sensor in a trackpad; and

a keyboard-timing sensor.

11. The method of claim 1 further comprising analyzing the feature vector to detect fraudulent activity.

12. The method of claim 1 , wherein:

said identifying comprises identifying the user as a first authorized user; and

the method further comprises, after said identifying:

determining that the device is being used by a second user instead of the first authorized user; and

authenticating and/or identifying the second user in response to a second trigger event.

13. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for authenticating and/or identifying a user of a portable electronic device, the method comprising:

in response to a trigger event, collecting sensor data from one or more sensors in the portable electronic device, wherein the sensor data includes movement-related sensor data caused by movement of the portable electronic device while the portable electronic device is in control of the user;

extracting a feature vector from the sensor data;

analyzing the feature vector using a model trained with sensor data previously obtained from the portable electronic device while the user was in control of the portable electronic device;

generating an associated security score for each of multiple authorized users of the device, based on said analysis of the feature vector; and

identifying the user based on the security scores;

wherein the trigger event comprises an adaptive notification sent at a variable interval determined based on feedback generated by a learner that processes the collected sensor data.

14. The non-transitory computer-readable storage medium of claim 13 ,

wherein the movement-related sensor data includes accelerometer data gathered while the user is walking; and

wherein the accelerometer data reflects a characteristic gait of the user while walking.

15. The non-transitory computer-readable storage medium of claim 13 , wherein the trigger event comprises a silent push notification received by the portable electronic device.

16. The non-transitory computer-readable storage medium of claim 13 , wherein the trigger event comprises a notification received by the portable electronic device from a wireless beacon.

17. The non-transitory computer-readable storage medium of claim 13 , wherein the trigger event comprises a periodic notification, which is sent at a predefined interval.

18. The non-transitory computer-readable storage medium of claim 13 , wherein:

the feedback relates to one or more of the following:

a change in confidence level for the identity of the user;

a battery level for the portable electronic device;

a usage pattern for the portable electronic device; and

a received notification associated with the portable electronic device.

19. The non-transitory computer-readable storage medium of claim 13 , wherein the trigger event comprises a detected activity of the user determined from the collected sensor data.

20. The non-transitory computer-readable storage medium of claim 13 , wherein the trigger event comprises a notification that the portable electronic device has entered or exited a predefined region associated with a geofence.

21. The non-transitory computer-readable storage medium of claim 13 , wherein the trigger event comprises one or more of the following:

a change in lighting;

a change in sound;

a change in magnetic field;

a detected keyword;

a detected near field communication (NFC) signal;

a received message notification;

a received telephone call;

a user-interaction event associated with the portable electronic device;

an interaction event between the portable electronic device and an external device/sensor;

a screen-on event;

a screen-off event;

a device-unlock event;

a device-unlock failure;

an application-opening event;

a switching-to-an-application event;

a switching cell towers event;

an install-application event;

an uninstall-application event;

a change in a device setting;

a screen brightness adjustment; and

a photograph-taking event.

22. The non-transitory computer-readable storage medium of claim 13 , wherein the method further comprising analyzing the feature vector to detect fraudulent activity.

23. A system that authenticates and/or identifies a user of a portable electronic device, comprising:

at least one processor and at least one associated memory; and

an authentication mechanism that executes on the at least one processor, wherein during operation, the authentication mechanism:

collects sensor data from one or more sensors in the portable electronic device in response to a trigger event, wherein the sensor data includes movement-related sensor data caused by movement of the portable electronic device while the portable electronic device is in control of the user;

extracts a feature vector from the sensor data;

analyzes the feature vector using a model trained with sensor data previously obtained from the portable electronic device while the user was in control of the portable electronic device;

generates an associated security score for each of multiple authorized users of the device, based on said analysis of the feature vector; and

identifies the user based on the security scores;

wherein the trigger event comprises an adaptive notification sent at a variable interval determined based on feedback generated by a learner that processes the collected sensor data.

24. The system of claim 23 ,

wherein the movement-related sensor data includes accelerometer data gathered while the user is walking; and

wherein the accelerometer data reflects a characteristic gait of the user while walking.

25. The system of claim 23 , wherein the trigger event comprises a silent push notification received by the portable electronic device.

26. The system of claim 23 , wherein the trigger event comprises a notification received by the portable electronic device from a wireless beacon.

27. The system of claim 23 , wherein the trigger event comprises a periodic notification, which is sent at a predefined interval.

28. The system of claim 23 , wherein:

the feedback relates to one or more of the following:

a change in confidence level for the identity of the user;

a battery level for the portable electronic device;

a usage pattern for the portable electronic device; and

a received notification associated with the portable electronic device.

29. The system of claim 23 , wherein the trigger event comprises a detected activity of the user determined from the collected sensor data.

30. The system of claim 23 , wherein the trigger event comprises a notification that the portable electronic device has entered or exited a predefined region associated with a geofence.

31. The system of claim 23 , wherein the trigger event comprises one or more of the following:

a change in lighting;

a change in sound;

a change in magnetic field;

a detected keyword;

a detected near field communication (NFC) signal;

a received message notification;

a received telephone call;

a user-interaction event associated with the portable electronic device;

an interaction event between the portable electronic device and an external device/sensor;

a screen-on event;

a screen-off event;

a device-unlock event;

a device-unlock failure;

an application-opening event;

a switching-to-an-application event;

a switching cell towers event;

an install-application event;

an uninstall-application event;

a change in a device setting;

a screen brightness adjustment; and

a photograph-taking event.

32. The system of claim 23 , wherein the authentication mechanism analyzes the feature vector to detect fraudulent activity.

33. A method for authenticating and/or identifying a user of a portable electronic device, the method comprising:

in response to each of multiple separate trigger events, collecting a set of sensor data from one or more sensors in the portable electronic device;

for each set of sensor data:

extracting a feature vector from the set of sensor data;

analyzing the feature vector using a model trained with sensor data previously obtained from the portable electronic device while the user was in control of the portable electronic device;

based on said analyzing, generating an associated security score for each of multiple types of device operations, including two or more of:

interaction between multiple devices in the vicinity of the user;

usage of a service by the user via the portable electronic device; and

one or more movements of the user while in control of the portable electronic device; and

authenticating and/or identifying the user based on the generated security scores;

wherein each trigger event comprises an adaptive notification sent at a variable interval determined based on a learner that processes the collected sensor data.

34. The method of claim 33 , wherein said interaction between multiple devices in the vicinity of the user includes one or more of:

membership of the multiple devices in the same network;

one or more characteristics of signals emitted by the multiple devices;

a combination of audio data collected by microphones of the multiple devices;

collection of ambient light data from light sensors of the multiple devices; and

one or more indications that one of the multiple devices is paired with at least one other of the multiple devices.

35. The method of claim 33 , wherein said usage of a service by the user via the portable electronic device includes one or more of:

a specific sequence of interactions with the service;

one or more mistakes performed by the user while using the service; and

behavior of the user in response to a display rendered by the service.

36. The method of claim 33 , wherein said one or more movements of the user while in control of the portable electronic device includes one or more of:

standing up;

sitting down;

typing on a device other than the portable electronic device; and

talking directly to a person.