Adaptive multi-factor authentication system

• US 9,912,657 B2
• Filed: 12/14/2015
• Issued: 03/06/2018
• Est. Priority Date: 06/02/2015
• Status: Active Grant

• Current Assignee: University of Memphis, University of Memphis Research Foundation
• Original Assignee: Abhijit Kumar Nag, Arunava Roy
• Inventors: Dasgupta, Dipankar, Nag, Abhijit Kumar, Roy, Arunava
• Primary Examiner(s): Song, Hosuk
• Application Number:
  US14/968,676
• Publication Number:
  US 20160359838A1
• Time in Patent Office: 813 Days
• Field of Search: 726 2- 7, 713168, 713182, 713185, 713186
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/36 by graphic or iconic representation
• CPC Class Codes: G06F 21/40 by quorum, i.e. whereby two or more security principals are required
• CPC Class Codes: G06F 21/45 Structures or tools for the administration of authentication
• CPC Class Codes: H04L 2463/082 applying multi-factor authentication
• CPC Class Codes: H04L 63/08 for authentication of entities cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32
• CPC Class Codes: H04L 63/083 using passwords cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226
• 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

Abstract

A system and methodology for adaptive selection of multiple modalities for authentication in different operating environments, thereby making authentication strategy unpredictable so to significantly reduce the risk of exploitation by authentication-guessing attacks. The system calculates trustworthiness values of different authentication factors under various environmental settings, and combines a trust-based adaptive, robust and scalable software-hardware framework for the selection of authentication factors for continuous and triggered authentication with optimal algorithms to determine the security parameters of each of the authentication factors. A subset of authentication factors thus are determined for application at triggering events on-the-fly, thereby leaving no exploitable a priori pattern or clue for hackers to exploit.

Claims

1. A machine for improved secure access to computing devices, systems, resources, or services, comprising:

one or more computer servers with authentication modality data stored thereon for a plurality of authentication modalities, wherein the authentication modality data for each authentication modality comprises a trustworthiness factor for each of one or more user input devices, a trustworthiness factor for each of one or more user connection media, and a computational complexity cost factor; and

a processor or microprocessor, wherein the processor or microprocessor is programmed to determine one or more of said authentication modalities to use for an authentication verification event by;

determining the objective trustworthiness value for each modality based on device trustworthiness factors and connection media trustworthiness factors for said modality;

determining a penalty value for each modality based on the computation complexity cost factor for said modality and the previous selection history of said modality for previous authentication verification events;

ranking the authentication modalities based on the objective trustworthiness value and the penalty value; and

applying one or more authentication modalities in order of ranking.

2. The machine of claim 1, wherein the user input devices comprise fixed devices, mobile devices, hand-held devices, or combinations thereof.

3. The machine of claim 1, wherein the user media environments comprise wired, wireless, cellular, or combinations thereof.

4. The machine of claim 1, wherein authentication modality data for each authentication modality comprises a list of features applicable to that authentication modality.

5. The machine of claim 4, wherein one or more features from said list of features are selected for an authentication modality for determining the objective trustworthiness value for that modality.

6. The machine of claim 1, wherein said authentication modalities comprise one or more of the following modalities:

facial recognition, fingerprint recognition, password, CAPTCHA, voice recognition, and keystroke analysis.

7. The machine of claim 1, wherein the plurality of authentication modalities comprises seven modalities:

facial recognition, fingerprint recognition, password, CAPTCHA, voice recognition, and keystroke analysis.

8. The machine of claim 1, wherein the processor or microprocessor further is programmed to modify one or more trustworthiness factors.

9. The machine of claim 1, wherein the authentication verification event is an initial request by a user using a user input device to access a computer device, system, resource, or service.

10. The machine of claim 1, wherein the authentication verification event is an automatic determination of whether to allow a user using a user input device to continue having access a computer device, system, resource, or service.