Granted Patent B1

US 10,482,223 · App. 15/073,691 · Granted Nov 19, 2019

Abstract

Claims (74)

1. A computer-implemented method for selecting questions for knowledge-based authentication based on social entropy, at least a portion of the method being performed by a computing device comprising at least one processor, the method comprising:

identifying a potential question to ask a user of a computing system during a Knowledge-Based Authentication (KBA) process in an attempt to verify the user's identity;

determining whether any information suggestive of a correct answer to the potential question is available to anyone other than the user of the computing system by determining whether any information suggestive of the correct answer is published online;

calculating a social entropy of the potential question based at least in part on the determination of whether any information suggestive of the correct answer is published online; and

ranking, with respect to social entropy, the potential question and at least one other potential question to ask the user of the computing system during the KBA process;

determining that the potential question is ranked higher than the other potential question with respect to social entropy;

selecting the potential question to be asked to the user during the KBA process due at least in part to the potential question being ranked higher than the other potential question with respect to social entropy; and

upon selecting the potential question, performing the KBA process by asking the user the potential question due at least in part to the potential question being ranked higher than the other potential question with respect to social entropy.

2. The method of claim 1 , wherein determining whether any information suggestive of the correct answer is available to anyone other than the user comprises:

identifying a level of information suggestive of the correct answer that is available to at least one person other than the user; and

determining that the level of information suggestive of the correct answer is below a certain informational threshold.

3. The method of claim 2 , wherein calculating the social entropy of the potential question comprises calculating the social entropy of the potential question as a function of the level of information suggestive of the correct answer.

4. The method of claim 1 , wherein determining whether any information suggestive of the correct answer is available to anyone other than the user comprises determining that no information suggestive of the correct answer is available to anyone other than the user.

5. The method of claim 1 , wherein:

calculating the social entropy of the potential question comprises determining that the social entropy of the potential question is above a certain entropy threshold; and

selecting the potential question to be asked to the user during the KBA process comprises selecting the potential question in response to the determination that the social entropy of the potential question is above the certain entropy threshold.

6. The method of claim 1 , wherein determining whether any information suggestive of the correct answer is available to anyone other than the user comprises at least one of:

determining whether any information suggestive of the correct answer is published on social media; and

determining whether any information suggestive of the correct answer is accessible to one or more people who have connected with the user on social media.

7. The method of claim 1 , further comprising:

identifying the other potential question to ask the user of the computing system during the KBA process;

determining a level of information suggestive of a correct answer to the other potential question that is available to at least one person other than the user;

determining that the level of information suggestive of the correct answer to the other potential question is above a certain informational threshold;

calculating a social entropy of the other potential question based at least in part on the determination that the level of information suggestive of the correct answer is above the certain informational threshold; and

preventing the other potential question from being asked to the user during the KBA process based at least in part on the social entropy of the potential question.

8. The method of claim 1 , further comprising:

identifying the other potential question to ask the user of the computing system during the KBA process;

determining a level of information suggestive of a correct answer to the other potential question that is available to at least one person other than the user; and

calculating a social entropy of the other potential question based at least in part on the determination that the level of information suggestive of the correct answer to the other potential question.

9. The method of claim 1 , further comprising identifying a context of the KBA process; and

wherein:

determining whether any information suggestive of the correct answer is available to anyone other than the user comprises determining that certain information suggestive of the correct answer is likely available to at least one person other than the user; and

calculating the social entropy of the potential question comprises:

determining that the certain information likely being available to the person other than the user is permissible in the context of the KBA process; and

in response to the determination that the certain information likely being available to the person other than the user is permissible in the context of the KBA process, disregarding the determination that the certain information is likely available to the person other than the user in the calculation of the social entropy of the potential question.

10. The method of claim 1 , wherein determining whether any information suggestive of the correct answer is available to anyone other than the user comprises at least one of:

checking for any information suggestive of the correct answer by way of crowdsourcing; and

crawling social media of the user for any information suggestive of the correct answer.

11. A system for selecting questions for knowledge-based authentication based on social entropy, the system comprising:

an identification module, stored in memory, that identifies a potential question to ask a user of a computing system during a Knowledge-Based Authentication (KBA) process in an attempt to verify the user's identity;

a determination module, stored in memory, that determines whether any information suggestive of a correct answer to the potential question is available to anyone other than the user of the computing system by determining whether any information suggestive of the correct answer is published online;

an entropy module, stored in memory, that:

calculates a social entropy of the potential question based at least in part on the determination of whether any information suggestive of the correct answer is published online; and

ranks, with respect to social entropy, the potential question and at least one other potential question to ask the user of the computing system during the KBA process;

wherein the determination module determines that the potential question is ranked higher than the other potential question with respect to social entropy;

a selection module, stored in memory, that selects the potential question to be asked to the user during the KBA process due at least in part to the potential question being ranked higher than the other potential question with respect to social entropy; and

at least one physical processor that:

is configured to execute the identification module, the determination module, the entropy module, and the selection module; and

performs the KBA process by asking the user the potential question due at least in part to the potential question being ranked higher than the other potential question with respect to social entropy.

12. The system of claim 11 , wherein:

the identification module identifies a level of information suggestive of the correct answer that is available to at least one person other than the user; and

the determination module determines that the level of information suggestive of the correct answer is below a certain informational threshold.

13. The system of claim 12 , wherein the entropy module calculates the social entropy of the potential question as a function of the level of information suggestive of the correct answer.

14. The system of claim 11 , wherein:

the entropy module determines that the social entropy of the potential question is above a certain entropy threshold; and

the selection module selects the potential question in response to the determination that the social entropy of the potential question is above the certain entropy threshold.

15. The system of claim 14 , wherein the determination module at least one of:

determines whether any information suggestive of the correct answer is published on social media; and

determines whether any information suggestive of the correct answer is accessible to one or more people who have connected with the user on social media.

16. The system of claim 11 , wherein:

the identification module identifies the other potential question to ask the user of the computing system during the KBA process;

the determination module:

determines a level of information suggestive of a correct answer to the other potential question that is available to at least one person other than the user; and

determines that the level of information suggestive of the correct answer to the other potential question is above a certain informational threshold;

the entropy module calculates a social entropy of the other potential question based at least in part on the determination that the level of information suggestive of the correct answer is above the certain informational threshold; and

the selection module prevents the other potential question from being asked to the user during the KBA process based at least in part on the social entropy of the potential question.

17. A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the computing device to:

identify a potential question to ask a user of a computing system during a Knowledge-Based Authentication (KBA) process in an attempt to verify the user's identity;

determine whether any information suggestive of a correct answer to the potential question is available to anyone other than the user of the computing system by determining whether any information suggestive of the correct answer is published online;

calculate a social entropy of the potential question based at least in part on the determination of whether any information suggestive of the correct answer is published online;

rank, with respect to social entropy, the potential question and at least one other potential question to ask the user of the computing system during the KBA process;

determine that the potential question is ranked higher than the other potential question with respect to social entropy;

select the potential question to be asked to the user during the KBA process due at least in part to the potential question being ranked higher than the other potential question with respect to social entropy; and

perform the KBA process by asking the user the potential question due at least in part to the potential question being ranked higher than the other potential question with respect to social entropy.

Assignments (6)