Context-aware adaptive authentication method and apparatus

Patent metadata

Field	Value
Publication number	US-9614843-B2
Application number	US-201214374202-A
Country	US
Kind code	B2
Filing date	Mar 8, 2012
Priority date	Mar 8, 2012
Publication date	Apr 4, 2017
Grant date	Apr 4, 2017

Abstract

A context-aware adaptive authentication method may comprise: determining a context for a user; adjusting automatically an authentication configuration for the user based at least in part on the context, wherein different matching accuracies of an authentication algorithm for the same authentication input data are associated with respective authentication configurations; and performing an authentication of the user with the authentication configuration, wherein for the user under a safe context, the authentication is performed by decreasing a matching accuracy of the authentication algorithm.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
determining a context for a user, the determining including collecting context information and modeling collected context information for the user;
adjusting automatically an authentication configuration for the user based at least in part on the modeled context, wherein different matching accuracies of an authentication algorithm for the same authentication input data are associated with respective authentication configurations; and
performing an authentication of the user with the authentication configuration, wherein for the user under a safe context, the authentication is performed by decreasing a matching accuracy of the authentication algorithm, the safe context having a plurality of security sub-levels, wherein the matching accuracy of the authentication algorithm is selected in accordance with a security sub-level in the plurality of security sub-levels associated with the safe context determined for the user;
wherein said decreasing the matching accuracy of the authentication algorithm further comprises:
employing a normal recognition model of the authentication algorithm for recognizing authentication input data from the user; and
determining the user as valid, in response to a match between at least a part of the recognized authentication input data and a corresponding part of authentication reference data of the authentication algorithm;

wherein at least one of the determining, the adjusting, and the performing is performed by at least one processor of at least one computing system.

2. The method according to claim 1 , wherein said determining the context for the user further comprises:
detecting whether the user is under the safe context based at least in part on the context information.

3. The method according to claim 1 , wherein the context further comprises at least one of a place, time, a background environment, a transportation status, and the time elapsed since a previous authentication becomes invalid.

4. The method according to claim 1 , wherein the at least part of the recognized authentication input data further comprises a beginning part of the authentication input data, and wherein the user is determined as valid without waiting for recognizing the remaining part of the authentication input data.

5. The method according to claim 1 , wherein said decreasing the matching accuracy of the authentication algorithm further comprises:
replacing a normal recognition model of the authentication algorithm with an imprecise recognition model for recognizing authentication input data from the user; and
determining the user as valid, in response to a match between the recognized authentication input data and authentication reference data of the authentication algorithm.

6. The method according to claim 1 , further comprising:
performing a re-authentication of the user under the same context by adjusting a current authentication configuration, in response to a failure of the authentication.

7. The method according to claim 1 , wherein the authentication further comprises at least one of: a text-based authentication, a voice-based authentication, a pattern-based authentication, a graph-based authentication and a biometric-based authentication.

8. The method according to claim 5 , wherein said replacing the normal recognition model of the authentication algorithm with the imprecise recognition model further comprises at least one of:
modifying one or more parameters of the normal recognition model; and
reducing one or more refining processes.

9. The method according to claim 6 , wherein said adjusting the current authentication configuration further comprises:
increasing a current matching accuracy of the authentication algorithm;
or applying another authentication algorithm which is more reliable than the authentication algorithm.

10. An apparatus, comprising:
at least one processor; and
at least one memory including computer program code,
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
determining a context for a user, the determining including collecting context information and modeling collected context information for the user;
adjusting automatically an authentication configuration for the user based at least in part on the modeled context, wherein different matching accuracies of an authentication algorithm for the same authentication input data are associated with respective authentication configurations; and
performing an authentication of the user with the authentication configuration, wherein for the user under a safe context, the authentication is performed by decreasing a matching accuracy of the authentication algorithm, the safe context having a plurality of security sub-levels, wherein the matching accuracy of the authentication algorithm is selected in accordance with a security sub-level in the plurality of security sub-levels associated with the safe context determined for the user;
wherein said decreasing the matching accuracy of the authentication algorithm further comprises:
employing a normal recognition model of the authentication algorithm for recognizing authentication input data from the user; and
determining the user as valid, in response to a match between at least a part of the recognized authentication input data and a corresponding part of authentication reference data of the authentication algorithm.

11. The apparatus according to claim 10 , wherein said determining the context for the user further comprises:
detecting whether the user is under the safe context based at least in part on the context information.

12. The apparatus according to claim 10 , wherein the context further comprises at least one of a place, time, a background environment, a transportation status, and the time elapsed since a previous authentication becomes invalid.

13. The apparatus according to claim 10 , wherein the at least part of the recognized authentication input data further comprises a beginning part of the authentication input data, and wherein the user is determined as valid without waiting for recognizing the remaining part of the authentication input data.

14. The apparatus according to claim 10 , wherein said decreasing the matching accuracy of the authentication algorithm further comprises:
replacing a normal recognition model of the authentication algorithm with an imprecise recognition model for recognizing authentication input data from the user; and
determining the user as valid, in response to a match between the recognized authentication input data and authentication reference data of the authentication algorithm.

15. The apparatus according to claim 10 , wherein the apparatus is caused to further perform:
performing a re-authentication of the user under the same context by adjusting a current authentication configuration, in response to a failure of the authentication.

16. The apparatus according to claim 14 , wherein said replacing the normal recognition model of the authentication algorithm with the imprecise recognition model further comprises at least one of:
modifying one or more parameters of the normal recognition model; and
reducing one or more refining processes.

17. The apparatus according to claim 15 , wherein said adjusting the current authentication configuration further comprises:
increasing a current matching accuracy of the authentication algorithm or
applying another authentication algorithm which is more

Assignees

• Jia Xu
• Cao Huanhuan
• Tian Jilei
• Liu Ying
• Nokia Technologies Oy

Inventors

• Jia Xu
• Cao Huanhuan
• Tian Jilei
• Liu Ying

Classifications

• H04L63/0876 Primary

  based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint · CPC title

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• G06F2221/2111

  Location-sensitive, e.g. geographical location, GPS · CPC title

• G06F21/31 Primary

  User authentication · CPC title