Patents by Inventor Devin Daniel REICH
Devin Daniel REICH has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11811794Abstract: 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.Type: GrantFiled: May 12, 2021Date of Patent: November 7, 2023Assignee: Sharecare AI, Inc.Inventors: 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
-
Patent number: 11755709Abstract: 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.Type: GrantFiled: February 21, 2022Date of Patent: September 12, 2023Assignee: SHARECARE AI, INC.Inventors: 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
-
Publication number: 20220415455Abstract: 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.Type: ApplicationFiled: August 26, 2022Publication date: December 29, 2022Applicant: SHARECARE AI, INC.Inventors: Srivatsa Akshay SHARMA, Walter Adolf DE BROUWER, Gabriel Gabra ZACCAK, Chethan R. SARABU, Devin Daniel REICH, Marina TITOVA, Andrés RODRÍGUEZ ESMERAL
-
Publication number: 20220337418Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic biometric identifiers. The method includes generating a scannable code upon receiving a success nonce from a registration server. The registration server can access a user identifier and a hash of at least a signature using the success nonce. The signature can be generated based at least in part upon a biometric identifier of a user. The method includes recreating the hash of the signature stored by the registration server. The method includes generating the scannable code by encrypting the success nonce and the recreated hash. The biometric identifier of the user is generated by feeding a plurality of non-deterministic biometric inputs to a trained machine learning model producing a plurality of feature vectors. The method includes projecting the plurality of feature vectors onto a surface of a unit hyper-sphere and computing a characteristic identity vector representing the user.Type: ApplicationFiled: November 15, 2021Publication date: October 20, 2022Applicant: Sharecare AI, Inc.Inventors: 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
-
Patent number: 11430547Abstract: 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.Type: GrantFiled: August 11, 2021Date of Patent: August 30, 2022Assignee: Sharecare AI, Inc.Inventors: Srivatsa Akshay Sharma, Walter Adolf De Brouwer, Gabriel Gabra Zaccak, Chethan R. Sarabu, Devin Daniel Reich, Marina Titova, Andrés Rodríguez Esmeral
-
Publication number: 20220269771Abstract: 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.Type: ApplicationFiled: May 2, 2022Publication date: August 25, 2022Applicant: SHARECARE AI, INC.Inventors: 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
-
Publication number: 20220179943Abstract: 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.Type: ApplicationFiled: February 21, 2022Publication date: June 9, 2022Applicant: SHARECARE AI, INC.Inventors: 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
-
Patent number: 11321447Abstract: 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.Type: GrantFiled: April 20, 2021Date of Patent: May 3, 2022Assignee: SHARECARE AI, INC.Inventors: 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
-
Patent number: 11256801Abstract: 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.Type: GrantFiled: April 20, 2021Date of Patent: February 22, 2022Assignee: doc.ai, Inc.Inventors: 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
-
Publication number: 20220051762Abstract: 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.Type: ApplicationFiled: August 11, 2021Publication date: February 17, 2022Applicant: Sharecare AI, Inc.Inventors: Srivatsa Akshay SHARMA, Walter Adolf DE BROUWER, Gabriel Gabra ZACCAK, Chethan R. SARABU, Devin Daniel REICH, Marina TITOVA, Andrés RODRÍGUEZ ESMERAL
-
Publication number: 20210360010Abstract: 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.Type: ApplicationFiled: May 12, 2021Publication date: November 18, 2021Applicant: Sharecare AI, Inc.Inventors: 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
-
Patent number: 11177960Abstract: 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.Type: GrantFiled: April 20, 2021Date of Patent: November 16, 2021Assignee: Sharecare AI, Inc.Inventors: 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
-
Publication number: 20210326422Abstract: 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.Type: ApplicationFiled: April 20, 2021Publication date: October 21, 2021Applicant: doc.ai, Inc.Inventors: 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
-
Publication number: 20210326433Abstract: 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.Type: ApplicationFiled: April 20, 2021Publication date: October 21, 2021Applicant: doc.ai, Inc.Inventors: 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
-
Publication number: 20210328801Abstract: 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.Type: ApplicationFiled: April 20, 2021Publication date: October 21, 2021Applicant: doc.ai, Inc.Inventors: 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
-
Publication number: 20210166111Abstract: The technology disclosed relates to a system and method for training processing engines. A processing engine can have at least a first processing module and a second processing module. The first processing module in each processing engine is different from a corresponding first processing module in every other processing engine. The second processing module in each processing engine is same as a corresponding second processing module in every other processing engine. The system can include a deployer that deploys each processing engine to a respective hardware module for training. The system can comprise a forward propagator which during forward pass stage can process inputs through first processing modules and produce an intermediate output for each first processing module. The system can comprise a backward propagator which during backward pass stage can determine gradients for each second processing module on corresponding final outputs and ground truths.Type: ApplicationFiled: December 1, 2020Publication date: June 3, 2021Applicant: doc.ai, Inc.Inventors: James Douglas Knighton, JR., Philip Joseph Dow, Marina Titova, Srivatsa Akshay Sharma, Walter Adolf De Brouwer, Joel Thomas Kaardal, Gabriel Gabra ZACCAK, Salvatore VIVONA, Devin Daniel REICH