Continuous user identification and situation analysis with identification of anonymous users through behaviormetrics

• US 20080098456A1
• Filed: 09/17/2007
• Published: 04/24/2008
• Est. Priority Date: 09/15/2006
• Status: Active Grant

• Current Assignee: Identity Metrics Incorporated
• Original Assignee: NeoKinetics Corp.
• Inventors: Hutchinson, Erik, Hust, Robert, Schmidt, Michael, Meehan, Timothy, Alward, Herbert, Straub, James
• Granted Patent: US 8,843,754 B2
• Time in Patent Office: Days
• US Class Current: 726/1
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour

Abstract

This invention discloses a system for determining whether a purported or alleged authorized user is in fact the authorized user, by comparing new data on a real-time basis against probability distribution representations including an authorized user probability distribution representation and a global or wide population probability distribution representation, to provide a probability as to whether the purported authorized user is the authorized user. This invention may utilize keyboard dynamics or data, or X-Y device data, or other data from similar measurable characteristics, to determine the probability that the new data from the purported authorized user indicates or identifies that user as the authorized user. This invention identifies the user continuously as the user interacts with the system and to identify a change in situation in the environment of the user. This invention provides a means to identify an anonymous user by matching the continuous recorded behaviormetrics or a characteristic of the anonymous user with the behaviormetrics of known users.

Claims

1. An authorized user authentication method, comprising:

accessing data from an authorized user;

using the data to create a first characteristic probability distribution representation indicative of the authorized user;

accessing situation data from the authorized user during a situation;

using the situation data to create a situation characteristic probability distribution representation indicative of the authorized user in a situation;

accessing new data from a purported authorized user;

comparing the new data of the purported authorized user to the first characteristic probability distribution representation for the authorized user;

determining a probability that the purported authorized user is the authorized user based on the comparing;

comparing the new data of the purported authorized user to the situation characteristic probability distribution representation for the authorized user; and

determining a probability that the purported authorized user is in the situation based on the comparing.

2. An authorized user authentication method as recited in claim 1, and further comprising:

providing a wide population first characteristic probability distribution representation indicative of the situation characteristic of a wide population;

comparing the new data of the purported authorized user to at least one of the situation characteristic probability distribution representation for the authorized user and the wide population situation characteristic probability distribution representation; and

determining a probability that the purported authorized user is the authorized user and is in the situation, based on the comparing.

3. An authorized user authentication method as recited in claim 2, and further wherein determining the probability that the purported authorized user is the authorized user through the application of Bayes Rule to the new data, the first characteristic probability distribution representation for the authorized user, and the wide population first characteristic probability distribution representation.

4. An authorized user authentication method as recited in claim 1, and further wherein the data is one of a keyboard dynamic and an X-Y device dynamic.

6. A method for matching a characteristic of an anonymous user to a characteristic of one of a plurality of users, comprising:

accessing data from each of a plurality of users;

using the data to create a plurality of first characteristic probability distribution representations indicative of each of the plurality of users;

accessing new data from an anonymous user;

comparing the new data to the plurality of first characteristic probability distribution representations indicative of each of the plurality of users; and

determining a probability that the anonymous user is one of the plurality of users based on the comparings.

5. An authorized user authentication method as recited in claim 6, and further wherein the X-Y device dynamic is one of a mouse use dynamic and a touchpad use dynamic.

7. A method for matching a characteristic of an anonymous user to a characteristic of one of a plurality of users,

accessing situation data from each of the plurality of users in a situation;

using the situation data to create a plurality of situation characteristic probability distribution representations indicative of each of the plurality of users in the situation;

accessing new situation data from an anonymous user;

comparing the new situation data to the plurality of situation characteristic probability distribution representations indicative of each of the plurality of users; and

determining a probability that the anonymous user is in the situation based on the comparing.

8. A method for matching a characteristic of an anonymous user to a characteristic of one of a plurality of users as recited in claim 7, and wherein the situation data used to create a plurality of first characteristic probability distribution representations indicative of each of the plurality of users is comprised of one of a keyboard dynamic and an X-Y device dynamic in the situation.

9. A method for matching a characteristic of an anonymous user to a characteristic of one of a plurality of users as recited in claim 7, and wherein the situation is one of a high stress situation and a high fatigue situation.