Identifying and authenticating users based on passive factors determined from sensor data
The disclosed embodiments relate to a system that authenticates and/or identifies a user of an electronic device based on passive factors, which do not require conscious user actions. During operation of the system, in response to detecting a trigger event, the system collects sensor data from one or more sensors in the electronic device. Next, the system extracts a feature vector from the sensor data. The system then analyzes the feature vector to authenticate and/or identify the user, wherein the feature vector is analyzed using a model trained with sensor data previously obtained from the electronic device while the user was operating the electronic device.
1. A method comprising:
receiving, at an authentication system, a set of feature vectors extracted from a set of sensors of an electronic device;
responsive to analyzing, at the authentication system, the set of feature vectors and/or a set of models of a set of behaviors of a user, determining, by the authentication system, a confidence value to indicate a likelihood that the user is in possession of the electronic device based, at least in part, on the set of feature vectors and/or the set of models;
responsive to the electronic device encountering a login form of a third party, modifying, by the authentication system, the login form through an alteration of a document object model, a structure, a look, a styling, or a combination thereof, of the login form;
responsive to the confidence value exceeding a threshold, authenticating, by the authentication system, the user based, at least in part, on the confidence value and the set of feature vectors and/or the set of models; and
transmitting, by the authentication system, a set of credentials to the third party, wherein:
the set of credentials are stored in memory, and
the set of credentials corresponds to the user.
2. The method of claim 1 , further comprising:
receiving, at an analysis component of the authentication system, the set of feature vectors; and
generating the set of models based, at least in part, on the set of feature vectors.
3. The method of claim 1 , wherein analyzing the set of feature vectors and the set of models occurs at a server coupled to a network.
4. The method of claim 1 , wherein modifying the login form comprises directing the electronic device to hide authentication-related elements displayed via the electronic device.
5. The method of claim 4 , further comprising:
directing the electronic device to display the login form responsive to the confidence value being not greater than the threshold.
6. The method of claim 5 , further comprising:
issuing a challenge to the electronic device responsive to the confidence value being not greater than the threshold.
7. The method of claim 1 , further comprising an analysis component of the authentication system querying a database service to obtain parameters of the user to build the set of models.
8. The method of claim 1 , wherein the set of sensors of the electronic device 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.
9. The method of claim 8 , wherein the accelerometer provides an output signal that is representative of a set of characteristics of the user's gait while the user is walking.
10. The method of claim 1 , wherein the set of feature vectors is received responsive to a trigger event comprising one or more of the following:
a detected activity of the user;
a state change associated with the electronic device;
a timer-based trigger; and
a broadcast trigger received by the electronic device.
11. An apparatus, comprising:
an authentication system computing platform, comprising at least one processor coupled to a memory device, to:
obtain, at the authentication system computing platform, a set of feature vectors extracted from a set of sensors of an electronic device;
responsive to an analysis, at the authentication system computing platform, the set of feature vectors and/or a set of models of a set of behaviors of a user, determine, by the authentication system computing platform, a confidence value to indicate a likelihood that the user is in possession of the electronic device the set of feature vectors and/or the set of models;
responsive to the electronic device encountering a login form of a third party, modify, by the authentication system computing platform, the login form through an alteration of a document object model, a structure, a look, a styling, or a combination thereof, of the login form;
responsive to the confidence value exceeding a threshold, authenticate, by the authentication system computing platform, the user based, at least in part, on the confidence value and the set of feature vectors and/or the set of models; and
transmit, by the authentication system computing platform, a set of credentials to the third party, wherein:
the set of credentials are stored in the memory device, and
the set of credentials correspond to the user.
12. The apparatus of claim 11 , wherein the authentication system computing platform is additionally to:
receive, at an analysis component, the set of feature vectors; and
generate the set of models based, at least in part, on the set of feature vectors.
13. The apparatus of claim 11 , wherein the authentication system computing platform is additionally to:
analyze the set of feature vectors and the set of models to determine the confidence value.
14. The apparatus of claim 11 , wherein the authentication system computing platform is additionally to:
direct the electronic device to hide authentication-related elements displayed via the electronic device.
15. The apparatus of claim 14 , wherein the authentication system computing platform is additionally to:
direct the electronic device to display the login form responsive to the confidence value being not greater than the threshold.
16. The apparatus of claim 15 , wherein the authentication system computing platform is additionally to:
issue a challenge to the electronic device responsive to the confidence value being not greater than the threshold.
17. The apparatus of claim 11 , wherein the authentication system computing platform is additionally to:
query a database service to obtain parameters of the user to build the set of models.
18. The apparatus of claim 11 , wherein the authentication system computing platform is additionally to obtain representations of output signals from 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.
19. The apparatus of claim 18 , wherein the accelerometer is to provide an output signal that is representative of one or more characteristics of the user's gait while the user is walking.
20. The apparatus of claim 11 , wherein the set of feature vectors is received responsive to a trigger event comprising one of the following:
a detected activity of the user;
a state change associated with the electronic device;
a timer-based trigger; and
a broadcast trigger received by the electronic device.