Context-dependent authentication system, method and device
A method for authenticating a user using a user device connected to a communications network, the method comprising an implicit phase, wherein said implicit phase comprises performing at least one task within a workflow, said at least one task necessary to move forward within said workflow; storing information associated with said performing of at least one task; comparing said stored information with a stored user profile; and determining whether said authentication of said user is successful or unsuccessful based on said comparing.
1. A method for authenticating a user of a computing device, the method being performed by one or more processors and comprising:
at a first time interval, developing a model for a first user, wherein developing the model includes (i) detecting performance of a task by the first user; (ii) determining a first set of characteristics for performance of the task by the first user; (iii) learning a first set of model parameters based on the first set of characteristics; and (iv) adjusting the model based on the first set of model parameters;
at a second time interval, detecting performance of the task on the computing device;
determining a score that is indicative of the task being performed by the first user, based at least in part on the model; and
performing an authentication operation based on a comparison of the score to a threshold;
wherein detecting performance of the task during the first time interval and the second time interval includes detecting a kinetic motion, using sensor data obtained from at least one an accelerometer or gyroscope of the computing device, and correlating the kinetic motion to the task based on contextual information obtained from at least one of a non-kinetic sensor of the computing device and/or an application that runs on the computing device.
2. The method of claim 1 , wherein the task is performed using one or more keys provided with the computing device.
3. The method of claim 2 , wherein the first set of characteristics is with respect to a key stroke velocity of the user.
4. The method of claim 3 , wherein the method is performed at least in part on a computer system that communicates with the computing device of the user over a network.
5. The method of claim 1 , wherein detecting performance of the task includes
monitoring the computing device of the user for user activity.
6. The method of claim 1 , wherein developing the model includes determining a behavior model for the first user performing the task.
7. The method of claim 1 , wherein the model differentiates between a manual entry and an automated entry.
8. The method of claim 1 , wherein the first set of characteristics include one or more dynamic characteristics for a type of kinetic motion performed by the user.
9. The method of claim 8 , wherein the type of kinetic motion includes a swipe on a screen of the computing device.
10. The method of claim 8 , wherein the type of kinetic motion includes the user moving the computing device to view a display of the computing device.
11. The method of claim 10 , wherein the computing device is a smart watch, and wherein the kinetic motion includes the user lifting the smart watch while worn to view the display.
12. The method of claim 8 , wherein the computing device is a mobile device, and the type of kinetic motion includes a gait of the user carrying the mobile device.
13. The method of claim 12 , wherein performing the authentication operation includes controlling access to the computing device.
14. The method of claim 13 , wherein performing the authentication operation includes controlling access to a mobile application installed on the mobile device.
15. A computer system comprising:
one or more processors;
a memory to store a set of instructions;
wherein the one or more processors access the set of instructions to perform operations comprising:
at a first time interval, developing a model for a first user, wherein developing the model includes (i) detecting performance of a task by the first user; (ii) determining a first set of characteristics for performance of the task by the first user; (iii) learning a first set of model parameters based on the first set of characteristics; and (iv) adjusting the model based on the first set of model parameters;
at a second time interval, detecting performance of the task on the computer system;
determining a score that is indicative of the task being performed by the first user, based at least in part on the model; and
performing an authentication operation based on a comparison of the score to a threshold; and
wherein detecting performance of the task during the first time interval and the second time interval includes detecting a kinetic motion, using sensor data obtained from at least one an accelerometer or gyroscope of the computer system, and correlating the kinetic motion to the task based on contextual information obtained from at least one of a non-kinetic sensor of the computer system and/or an application that runs on the computer system.
16. The computer system of claim 15 , wherein the computer system includes a mobile device of the user.
17. The computer system of claim 16 , wherein detecting performance of the task includes detecting one or more dynamic characteristics using one or more sensors of the mobile device on which the task is performed.
18. A non-transitory computer readable medium that stores instructions, which when executed by one or more processors of a computer system, cause the computer system to perform operations that include:
at a first time interval, developing a model for a first user, wherein developing the model includes (i) detecting performance of a task by the first user; (ii) determining a first set of characteristics for performance of the task by the first user; (iii) learning a first set of model parameters based on the first set of characteristics; and (iv) adjusting the model based on the first set of model parameters;
at a second time interval, detecting performance of the task on computer system;
determining a score that is indicative of the task being performed by the first user based at least in part on the model; and
performing an authentication operation based on a comparison of the score to a threshold;
wherein detecting performance of the task during the first time interval and the second time interval includes detecting a kinetic motion, using sensor data obtained from at least one an accelerometer or gyroscope of the computer system, and correlating the kinetic motion to the task based on contextual information obtained from at least one of a non-kinetic sensor of the computer system and/or an application that runs on the computer system.
19. The non-transitory computer readable medium of claim 18 , wherein the computer system includes a mobile device of a user.