Method for modeling user possession of mobile device for user authentication framework

• US 9,781,106 B1
• Filed: 11/19/2014
• Issued: 10/03/2017
• Est. Priority Date: 11/20/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Knowles Electronics Llc (Knowles Corporation)
• Inventors: Vitus, Deborah, Murgia, Carlo, Steele, James, Caldwell, Frederic
• Primary Examiner(s): Hirl, Joseph P
• Assistant Examiner(s): Shirazi, Sayed Beheshti
• Application Number:
  US14/548,207
• Time in Patent Office: 1,049 Days
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06F 21/34 involving the use of external additional devices, e.g. dongles or smart cards
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04W 12/065 Continuous authentication

Abstract

Method and systems for modeling user possession of a mobile device for a user authentication framework are provided. The method includes analyzing sensor data representing information captured from sensor(s) associated with at least one of a plurality of devices, the plurality including the user'"'"'s mobile device. The method allows for determining, based on the analyzed sensor data, a probability that the user maintains possession of the user'"'"'s mobile device; and configuring the probability for use in determining whether to require authentication. The determination may include configuring a probabilistic model that includes a first state indicating that the user possesses the mobile device and a second state indicating that the user does not; classifying motions of the mobile device by types, the motions being determined based on the sensor data; and updating probabilities of the two states in response to determining that at least one of the motions has occurred.

Claims

1. A method for modeling user possession of a mobile device for a user authentication framework, the method comprising:

analyzing sensor data, the sensor data representing information captured from sensors associated with at least two of a plurality of devices;

determining, based on the analyzed sensor data, a probability that the user is in possession of the mobile device, the mobile device being one of the plurality of the devices; and

configuring the probability for use in determining whether to require authentication,

wherein the determination of the probability that the user is in possession of the mobile device is further based on an analysis of a difference between a first action of the user represented by the sensor data associated with a first one of the two devices and a second action of the user represented by the sensor data associated with a second one of the two devices;

allowing the user to access a first set of functionality of the mobile device without requiring authentication based on the determined probability being higher than a first threshold; and

requiring the user to perform authentication in order to access a second set of functionality of the mobile device based on the determined probability being lower than a second threshold.

2. The method of claim 1, wherein devices of the plurality of the devices are communicatively coupled via a network and operable to exchange the sensor data with each other.

3. The method of claim 1, wherein the sensors include at least one of the following:

motion sensors, inertial sensors, visual sensors, location sensors, bio sensors, audio sensors, and proximity sensors.

4. The method of claim 1, wherein the sensor data comprises a representation of a feed from one or more social networks.

5. The method of claim 1, wherein the determining probability that user possesses the mobile device comprises:

configuring a first probabilistic model, the first probabilistic model including at least two states, the at least two states including a first state indicating that the user possesses the mobile device and a second state indicating that the user does not possess the mobile device;

classifying motions of the mobile device by types, the motions being determined based on the sensor data received from one or more devices of the plurality of the devices; and

updating probabilities of the at least two states in response to determining that at least one of the motions has occurred.

6. The method of claim 5, wherein the probabilities of the at least two states are updated based on a type of the at least one of the motions, probability of determining the at least one of the motions, and a number of motions occurring in a pre-determined time period.

7. The method of claim 5, further comprising:

determining a location of the mobile device relative to the user, the location of the mobile device being determined based on the sensor data using a second probabilistic model; and

adjusting the probability of the at least two states and probabilities of determining the motions based on the determined location of the mobile device.

9. The method of claim 1, wherein the determined probability is further configured for use in granting access to a number and a type of applications.

10. The method of claim 5, wherein a location of the mobile device with respect to the user and the probabilities of the two states are provided to the mobile device to facilitate determining whether to require the user to provide active authentication in the form of at least one of credentials and a fingerprint.

11. The method of claim 1, further comprising:

based upon the determining, based on the analyzed sensor data, of the probability that the user is in possession of the mobile device, causing a reduction of power consumption of the mobile device.

8. A method, for modeling user possession of a mobile device for a user authentication framework, the method comprising:

analyzing sensor data, the sensor data representing information captured from one or more sensors associated with at least one of a plurality of devices;

determining, based on the analyzed sensor data, a probability that the user is in possession of the mobile device, the mobile device being one of the plurality of the devices; and

configuring the probability for use in determining whether to require authentication, wherein the determining probability that user possesses the mobile device comprises;

configuring a first probabilistic model, the first probabilistic model including at least two states, the at least two states including a first state indicating that the user possesses the mobile device and a second state indicating that the user does not possess the mobile device;

classifying motions of the mobile device by types, the motions being determined based on the sensor data received from one or more devices of the plurality of the devices; and

updating probabilities of the at least two states in response to determining that at least one of the motions has occurred, and

wherein probabilities of the at least two states are reset to predetermined initial values using a user authentication mechanism of the mobile device provided by an original equipment manufacturer;

allowing the user to access a first set of functionality of the mobile device without requiring authentication based on the determined probability being higher than a first threshold; and

requiring the user to perform authentication in order to access a second set of functionality of the mobile device based on the determined probability being lower than a second threshold.

12. A system for modeling user possession of a mobile device for a user authentication framework, the system comprising a plurality of devices including the mobile device, the mobile device comprising:

a processor; and

a memory communicatively coupled to the processor, the memory storing instructions which when executed by the processor perform a method comprising;

analyzing sensor data, the sensor data representing information captured from sensors associated with at least two of a the plurality of devices;

determining, based on the analyzed sensor data, a probability that the user is in possession of the mobile device; and

configuring the probability for use in determining whether to require authentication,

wherein the determination of the probability that the user is in possession of the mobile device is further based on an analysis of a difference between a first action of the user represented by the sensor data associated with a first one of the two devices and a second action of the user represented by the sensor data associated with a second one of the two devices;

allowing the user to access a first set of functionality of the mobile device without requiring authentication based on the determined probability being higher than a first threshold; and

requiring the user to perform authentication in order to access a second set of functionality of the mobile device based on the determined probability being lower than a second threshold.

13. The system of claim 12, wherein devices of the plurality of the devices are communicatively coupled via a network and operable to exchange the sensor data with each other.

14. The system of claim 12, wherein the sensors include at least one of the following:

motion sensors, inertial sensors, visual sensors, location sensors, bio sensors, audio sensors, proximity sensors, and a feed from one or more social networks.

15. The system of claim 12, wherein determining probability that user possesses the mobile device comprises:

configuring a first probabilistic model, the first probabilistic model including at least two states, the at least two states including a first indicative of the user possessing the mobile device and a second state indicative of the user not possessing the mobile device;

classifying motions of the mobile device by types, the motions being determined based on the sensor data received from one or more devices of the plurality of the devices; and

updating probabilities of the at least two states in response to determining that at least one of the motions has occurred.

16. The system of claim 15, wherein the probabilities of the at least two states are updated based on type of at least one of the motions, a probability of determining the at least one of the motions, and a number of motions occurring in a pre-determined time period.

17. The system of claim 15, further comprising:

determining a location of the mobile device relative to the user, the location of the mobile device being determined based on the sensor data using a second probabilistic model; and

adjusting the probability of the at least of two states and probabilities of determining the motions based on the determined location of the mobile device.

18. A non-transitory computer-readable storage medium having embodied thereon instructions, which when executed by one or more processors, perform a method modeling user possession of a mobile device for a user authentication framework, the method comprising:

analyzing sensor data, the sensor data representing information captured from one or more sensors associated with at least two of a plurality of devices;

determining, based on the analyzed sensor data, a probability that the user is in possession of the mobile device, the mobile device being one of the plurality of the devices; and

configuring the probability for use in determining whether to require authentication,

wherein the determination of the probability that the user is in possession of the mobile device is further based on an analysis of a difference between a first action of the user represented by the sensor data associated with a first one of the two devices and a second action of the user represented by the sensor data associated with a second one of the two devices;

allowing the user to access a first set of functionality of the mobile device without requiring authentication based on the determined probability being higher than a first threshold; and

requiring the user to perform authentication in order to access a second set of functionality of the mobile device based on the determined probability being lower than a second threshold.