公开(公告)号：US11755709B2

公开(公告)日：2023-09-12

申请号：US17676797

申请日：2022-02-21

Applicant: SHARECARE AI, INC.

Inventor： Axel Sly ,  Srivatsa Akshay Sharma ,  Brett Robert Redinger ,  Devin Daniel Reich ,  Geert Trooskens ,  Meelis Lootus ,  Young Jin Lee ,  Ricardo Lopez Arredondo ,  Frederick Franklin Kautz, IV ,  Satish Srinivasan Bhat ,  Scott Michael Kirk ,  Walter Adolf De Brouwer ,  Kartik Thakore

IPC: G06F21/32 ,  G06F21/45 ,  G06N20/00 ,  H04L9/32 ,  G16H10/60 ,  G06K7/14 ,  G06N5/04 ,  H04L9/08 ,  G06V40/70 ,  G06K19/06 ,  G06F18/214 ,  G06V10/74 ,  G06V10/77 ,  G06V10/80 ,  G06V10/44 ,  G06V40/16 ,  G06V10/774 ,  H04L9/40 ,  G06N3/08 ,  G06N3/04

CPC classification number: G06F21/32 ,  G06F18/214 ,  G06F21/45 ,  G06K7/1417 ,  G06K19/06037 ,  G06N5/04 ,  G06N20/00 ,  G06V10/451 ,  G06V10/761 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/803 ,  G06V40/161 ,  G06V40/168 ,  G06V40/70 ,  G16H10/60 ,  H04L9/085 ,  H04L9/0841 ,  H04L9/0866 ,  H04L9/0894 ,  H04L9/3228 ,  H04L9/3231 ,  H04L9/3236 ,  H04L9/3239 ,  H04L9/3242 ,  H04L9/3247 ,  H04L9/3297 ,  G06N3/04 ,  G06N3/08 ,  H04L63/0861

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

公开(公告)号：US11177960B2

公开(公告)日：2021-11-16

申请号：US17235889

申请日：2021-04-20

Applicant: Sharecare AI, Inc.

Inventor： Axel Sly ,  Srivatsa Akshay Sharma ,  Brett Robert Redinger ,  Devin Daniel Reich ,  Geert Trooskens ,  Meelis Lootus ,  Young Jin Lee ,  Ricardo Lopez Arredondo ,  Frederick Franklin Kautz, IV ,  Satish Srinivasan Bhat ,  Scott Michael Kirk ,  Walter Adolf De Brouwer ,  Kartik Thakore

IPC: H04L9/32 ,  H04L9/08 ,  G06N20/00 ,  G06K7/14 ,  G06N5/04

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

公开(公告)号：US11811794B2

公开(公告)日：2023-11-07

申请号：US17319025

申请日：2021-05-12

Applicant: Sharecare AI, Inc.

Inventor： Gabriel Gabra Zaccak ,  William Hartman ,  Andrés Rodriguez Esmeral ,  Devin Daniel Reich ,  Marina Titova ,  Brett Robert Redinger ,  Philip Joseph Dow ,  Satish Srinivasan Bhat ,  Walter Adolf De Brouwer ,  Scott Michael Kirk

IPC: H04L9/40 ,  G06N20/20

CPC classification number: H04L63/1416 ,  G06N20/20

Abstract: The technology disclosed provides systems and methods related to preventing exfiltration of training data by feature reconstruction attacks on model instances trained on the training data during a training job. The system comprises a privacy interface that presents a plurality of modulators for a plurality of training parameters. The modulators are configured to respond to selection commands via the privacy interface to trigger procedural calls. The procedural calls modify corresponding training parameters in the plurality of training parameters for respective training cycles in the training job. The system comprises a trainer configured to execute the training cycles in dependence on the modified training parameters. The trainer can determine a performance accuracy of the model instances for each of the executed training cycles. The system comprises a differential privacy estimator configured to estimate a privacy guarantee for each of the executed training cycles in dependence on the modified training parameters.

公开(公告)号：US11430547B2

公开(公告)日：2022-08-30

申请号：US17400079

申请日：2021-08-11

Applicant: Sharecare AI, Inc.

Inventor： Srivatsa Akshay Sharma ,  Walter Adolf De Brouwer ,  Gabriel Gabra Zaccak ,  Chethan R. Sarabu ,  Devin Daniel Reich ,  Marina Titova ,  Andrés Rodríguez Esmeral

IPC: G16H10/20 ,  H04L9/08 ,  G06F7/523 ,  G06F7/58 ,  G06F7/483

Abstract: The technology disclosed relates to a system and method for assigning participants to groups in a clinical trial. The system includes a federated server configured with group assignability data specifying a plurality of groups assignable to participants in a clinical trial and group distribution data specifying distribution of the participants into groups. The groups include at least one placebo group and one or more treatment groups. The system includes an intervention server configured to generate group encryption keys for encrypting the group assignability data. The system includes edge devices of each of the participants. The edge devices are in communication with the federated server.

公开(公告)号：US11321447B2

公开(公告)日：2022-05-03

申请号：US17235876

申请日：2021-04-20

Applicant: SHARECARE AI, INC.

Inventor： Axel Sly ,  Srivatsa Akshay Sharma ,  Brett Robert Redinger ,  Devin Daniel Reich ,  Geert Trooskens ,  Meelis Lootus ,  Young Jin Lee ,  Ricardo Lopez Arredondo ,  Frederick Franklin Kautz, IV ,  Satish Srinivasan Bhat ,  Scott Michael Kirk ,  Walter Adolf De Brouwer ,  Kartik Thakore

IPC: G06K9/00 ,  G06F21/45 ,  G06N20/00 ,  H04L9/32 ,  G16H10/60 ,  G06F21/32 ,  G06K9/62 ,  G06K7/14 ,  G06N5/04 ,  H04L9/08 ,  H04L29/06 ,  G06N3/08 ,  G06N3/04

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.