Guided implicit authentication

1. A computer-implemented method for guided implicit authentication, the method comprising:

receiving, by a computing device, a request to access a controlled resource from a user;

determining current contextual data associated with the request;

determining whether the current contextual data associated with the user request is inconsistent with regular user behavior by calculating a user behavior measure derived from historical contextual data of past user events;

responsive to the current contextual data being inconsistent with regular user behavior, prompting the user to confirm whether the current contextual data is safe for implicit authentication;

providing a user interface for the user to input regular user behavior and expected behavior changes;

updating the user behavior measure based on the user input; and

responsive to the user confirming that the current contextual data is safe for implicit authentication, updating the user behavior measure based on the current contextual data.

2. The method of claim 1 , wherein calculating the user behavior measure comprises determining a scale indicating the likelihood of an event happening associated with the user in a given context.

3. The method of claim 1 , further comprising:

deriving user behavior changes from user contextual data.

4. The method of claim 1 , wherein the contextual data of the user comprise one or more of: location data, time data, calendar information, social network information, communication information, and online data.

5. The method of claim 1 , wherein prompting the user to confirm that current contextual data is safe for authentication further comprises requesting the confirmation from another device associated with the user.

6. The method of claim 1 , further comprising:

responsive to the determined inconsistency of the user request, alerting the user through an email.

7. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for guided implicit authentication, the method comprising:

receiving a request to access a controlled resource from a user;

determining current contextual data associated with the request;

determining whether the current contextual data associated with the user request is inconsistent with regular user behavior by calculating a user behavior measure derived from historical contextual data of past user events;

responsive to the current contextual data being inconsistent with regular user behavior, prompting the user to confirm whether the current contextual data is safe for implicit authentication;

providing a user interface for the user to input regular user behavior and expected behavior changes;

updating the user behavior measure based on the user input; and

responsive to the user confirming that the current contextual data is safe for implicit authentication, updating the user behavior measure based on current contextual data.

8. The non-transitory computer-readable storage medium of claim 7 , wherein calculating the user behavior measure comprises determining a scale indicating the likelihood of an event happening associated with the user in a given context.

9. The non-transitory computer-readable storage medium of claim 7 , wherein the method further comprises:

deriving user behavior changes from user contextual data.

10. The non-transitory computer-readable storage medium of claim 7 , wherein the contextual data of the user comprise one or more of: location data, time data, calendar information, social network information, communication information, and online data.

11. The non-transitory computer-readable storage medium of claim 7 , wherein prompting the user to confirm that current contextual data is safe for authentication further comprises requesting the confirmation from another device associated with the user.

12. The non-transitory computer-readable storage medium of claim 7 , wherein the method further comprises:

responsive to the determined inconsistency of the user request, alerting the user through an email.

13. A system for guided implicit authentication, the system comprising:

an access request receiver configured to receive a request from a user to access a controlled resource;

a determination mechanism configured to determining current contextual data associated with the request, and to determine whether the current contextual data associated with the user request is inconsistent with regular user behavior by calculating a user behavior measure derived from historical contextual data of past user events;

a user interface configured to:

prompt the user to confirm whether the current contextual data is safe for implicit authentication, in response to the current contextual data being inconsistent with regular user behavior; and

provide a user interface for the user to input regular user behavior and expected behavior changes; and

an updating mechanism configured to:

update the user behavior measure based on current contextual data, in response to the user confirming that the current contextual data is safe for implicit authentication; and

update the user behavior measure based on the user input.

14. The system of claim 13 , wherein while calculating the user behavior measure, the determination mechanism is configured to determine a scale indicating the likelihood of an event happening associated with the user in a given context.

15. The system of claim 13 , further comprising:

a derivation mechanism configured to derive user behavior changes from user contextual data.

16. The system of claim 13 , wherein the contextual data of the user comprise one or more of: location data, time data, calendar information, social network information, communication information, and online data.

17. The system of claim 13 , wherein while prompting the user to confirm that current contextual data is safe for authentication, the user interface is further configured to request the confirmation from another device associated with the user.

18. The system of claim 13 , further comprising:

a warning mechanism configured to, responsive to the determined inconsistency of the user request, alert the user through an email.