US 12,386,938 B2
Authentication using a biometric template related to neural activity, and applications thereof
Gideon Littwin, Tel-Aviv (IL); Hagai Lalazar, Tel-Aviv (IL); Nizan Klinghoffer, Giv'atayim (IL); Jonathan Berrebi, Tel-Aviv (IL); and Ilay Gordon, Ramat Gan (IL)
Assigned to COGNTIV Neurosystems Ltd., Tel-Aviv (IL)
Filed by COGNTIV Neurosystems Ltd., Tel-Aviv (IL)
Filed on Dec. 27, 2024, as Appl. No. 19/003,945.
Claims priority of provisional application 63/616,165, filed on Dec. 29, 2023.
Prior Publication US 2025/0217465 A1, Jul. 3, 2025
Int. Cl. G06F 21/32 (2013.01); G16H 40/63 (2018.01)
CPC G06F 21/32 (2013.01) [G16H 40/63 (2018.01)] 9 Claims
OG exemplary drawing
 
1. A computer-implemented method for authenticating a user, comprising:
during enrollment:
(a) receiving a first electroencephalogram (EEG) data collected from a headset comprising sensors attached to or near the user's head;
(b) inputting the first EEG data into a first machine learning model to determine a first biometric template related to neural activity, the first machine learning model trained using a first training data set of additional EEG data from data collection participants to maximize distinctiveness;
(c) when an enrollment stimulus or instruction is presented to the user to engage in a calibration task, receiving a second EEG data collected from the sensors;
(d) inputting the second EEG data into a second machine learning model to determine a second biometric template related to neural activity, the second machine learning model trained using a second training data set of additional EEG data from the data collection participants performing the calibration task;
repeatedly while the user is wearing the headset:
(e) receiving a third EEG data measured from the sensors of the headset;
(f) inputting the third EEG data into the first machine learning model to determine a third biometric template related to the neural activity;
(g) comparing the first and third biometric templates to determine the user's identity;
(h) when the comparing (g) determines the user wearing the headset is not who is logged in, locking the headset;
(i) receiving an input to conduct an activity on the headset requiring heightened authentication; and
(j) in response to a requirement for an additional authentication factor to verify the user's identity, comparing the second and third biometric templates to authenticate the user's identity.