US 12,306,918 B2
Cognitive multi-factor authentication
Chad Steelberg, Costa Mesa, CA (US); and Albert Brown, San Juan Capistrano, CA (US)
Assigned to VERITONE, INC., Irvine, CA (US)
Filed by VERITONE, INC., Denver, CO (US)
Filed on Nov. 30, 2021, as Appl. No. 17/538,988.
Application 17/538,988 is a continuation of application No. PCT/US2020/035484, filed on May 31, 2020.
Claims priority of provisional application 62/855,796, filed on May 31, 2019.
Prior Publication US 2022/0269761 A1, Aug. 25, 2022
Int. Cl. G06F 21/32 (2013.01); G06F 3/01 (2006.01); G06F 21/40 (2013.01); G06V 40/16 (2022.01); G06V 40/70 (2022.01)
CPC G06F 21/32 (2013.01) [G06F 3/017 (2013.01); G06F 21/40 (2013.01); G06V 40/172 (2022.01); G06V 40/70 (2022.01); G06F 2221/2113 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for authenticating a user, the method comprising:
requesting the user to verify identity using a first mode, wherein the first mode comprises one of a password verification process, a fingerprint verification process, a voice verification process, or a iris verification process;
analyzing a continuous video stream of the user, using a facial identification engine, to verify the user identity;
requesting the user to perform an action while maintaining the continuous video stream;
analyzing the continuous video stream, using the second engine, to verify that the requested action is performed by the user; and
authenticating the user based on results of the first mode, the facial identification engine, and the second engine,
wherein the continuous video stream is analyzed using a multi-stage authentication process that includes sequential verification steps, with each step focused on different biometric features of the user,
wherein the system provides real-time feedback to the user regarding the performed action and prompts the user to repeat the action if the action does not meet a predetermined threshold for successful authentication,
wherein the continuous video stream is analyzed in conjunction with additional data streams, including biometric sensor data, to enhance the confidence score associated with the user authentication,
wherein the system continuously monitors facial expressions during the video stream and analyzes the expressions to detect any discrepancies with expected user behavior, and
wherein the authentication thresholds are adjusted dynamically based on user-specific historical data, wherein previous authentication attempts are used to modify the criteria for future authentication sessions.