International Business Machines Corporation

John F Behnken

Jeb R Linton

Michael Amisano

John Melchionne

David K Wright

Mauro Marzorati

Dennis Kramer

Aaron K Baughman

Mohamed Nooman Ahmed

David B Kumhyr

Yaser K Doleh

Michael T Fiori

James R Kozloski

Rhonda L Childress

Louie Arthur Dickens

Michael John Spisak

Rodolfo Lopez

William A Mills

Srishti Arora

A first patient intervention is identified. The first patient intervention regards a first patient record that includes one or more attributes related to a first patient. The first patient intervention is transmitted to a first program split of a secure multi-party computation. A conflict is detected in the first patient intervention and an existing medical situation regarding the first patient. The conflict is detected by the first program split of the secure multi-party computation and by a third program split of the secure multi-party computation. Based on the detected conflict, a notification is generated by the first program split. The notification is based on the detected conflict. The notification based on the detected conflict is provided to a first client.

Medical intervention based on separate data sets

Methods for cellular network authentication utilizing unlinkable anonymous credentials are disclosed. In embodiments, a method includes: contacting, by a computing device, a mobile device network with a request to connect to the mobile device network; conducting, by the computing device, an interactive credential issuance protocol with an Issuer of the mobile device network to generate an unlinkable anonymous credential; and connecting, by the computing device, to the mobile device network based on a Verifier of the mobile device network verifying the computing device based on the unlinkable anonymous credential.

Cellular network authentication utilizing unlinkable anonymous credentials

Technology for voting, or endorsing with votes, a set of subjects under review, such as a group of human individual peers or a set of products. Each voter in this system is provided with an amount of voting credits that may be allocated among and between at least some of the subjects under review. In some embodiments a discounting scheme is applied to the voting credit allocations so that multiple credits allocated to a single subject will typically count for fewer net 'votes' for the subject as the number of credits allocated to that single subject increases. In some embodiments, the discounting scheme is polynomial voting.

Peer review system with polynomial discounting

Embodiments are disclosed for a method for private transfer learning. The method includes generating a machine learning model comprising a training application programming interface (API) and an inferencing API. The method further includes encrypting the machine learning model using a predetermined encryption mechanism. The method additionally includes copying the encrypted machine learning model to a trusted execution environment. The method also includes executing the machine learning model in the trusted execution environment using the inferencing API.

Private transfer learning

A method, apparatus and computer program product to detect whether specific sensitive data of a client is present in a cloud computing infrastructure is implemented without requiring that data be shared with the cloud provider, or that the cloud provider provide the client access to all data in the cloud. Instead of requiring the client to share its database of sensitive information, preferably the client executes a tool that uses a cryptographic protocol, namely, Private Set Intersection (PSI), to enable the client to detect whether their sensitive information is present on the cloud. Any such information identified by the tool is then used to label a document or utterance, send an alert, and/or redact or tokenize the sensitive data.

Secure multiparty detection of sensitive data using private set intersection (PSI)

Training a deep neural network model using a trusted execution environment is provided. A selection of two or more encrypted files owned by different entities within a plurality of encrypted files containing sensitive datasets is made by a user of a client device. The two or more encrypted files owned by the different entities are decrypted within the trusted execution environment to form decrypted sensitive datasets owned by the different entities. The decrypted sensitive datasets owned by the different entities are combined within the trusted execution environment to form combined sensitive data owned by the different entities. The deep neural network model is generated within the trusted execution environment based on the combined sensitive data owned by the different entities. The deep neural network model is trained within the trusted execution environment using the combined sensitive data owned by the different entities.

Blockchain-enabled decentralized ecosystem for secure training of deep neural networks using trusted execution environments

Methods for secure data monitoring utilizing secure private set intersections are disclosed. In embodiments, a computer-implemented method includes: generating a garbled circuit program compiled into a first and second half; sending the second half of the garbled circuit program to a client server of a client; receiving social network data from a social network provider; and generating search results, utilizing the first half of the garbled circuit program in cooperation with the second half of the garbled circuit program, based on client data input at the second half of the garbled circuit program. The client data is private with respect to the social network provider and the social network data is private with respect to the client.

Secure data monitoring utilizing secure private set intersection

Systems for secure data monitoring utilizing secure private set intersections are disclosed. In embodiments, program instructions are executable by a computing device to cause the computing device to: generate a garbled circuit program compiled into a first half and a second half; send the second half of the garbled circuit program to a client server of a client; receive social network data from a social network provider; index, utilizing the first half of the garbled circuit program in cooperation with the second half of the garbled circuit program at the client server, the social network data based on predetermined intent categories; and generate search results, utilizing the first half of the garbled circuit program in cooperation with the second half of the garbled circuit program at the client server, based on client data at the second half of the garbled circuit program.

Enforcing authorization controls for an approved software change on a target system is provided. A user is validated to perform a set of actions. The set of actions performed by the validated user is monitored to determine whether the set of actions conform to an approved process for the approved software change on the target system. A deviation from the approved process is detected based on determining that the set of actions do not conform to the approved process during the monitoring. In response to detecting the deviation from the approved process, an alert is sent regarding the deviation.

Enforcing primary and secondary authorization controls using change control record identifier and information

In one embodiment, a method includes limiting functionality of a remote controlled device during a first period of time where a user of the remote controlled device is not authenticated, receiving, from a separate authentication device, identity information of the user of the remote controlled device and information of the remote controlled device via an authentication process, authenticating the user prior to allowing full functionality of the remote controlled device, sending an indication of the identity of the user to the remote controlled device; and in response to determining during the authenticating that the user is verified as a trainee for the remote controlled device, enabling a trainer/trainee setting that allows a trainer to provide control of the remote controlled device to the trainee without functionality of the remote controlled device being limited.

Authentication of users for securing remote controlled devices

A method for implementing a secure system to prevent adverse drug interactions and repeat prescriptions, for a patient, in a multi-party computing environment. The method includes receiving a patient identifier from a provider, authenticating an access by the provider, and retrieving a second patient identifier, wherein the second patient identifier corresponds to the received patient identifier, wherein the received patient identifier and the second patient identifier are different. The method further includes receiving an input from the provider that corresponds to the patient identifier, and accessing a database that contains a stored private ID, wherein the stored private ID is a combination of the received patient identifier and the retrieved second patient identifier, and wherein the database includes data relating to the patient. The method includes searching the database to obtain a search result based on the received input from the provider, and transmitting the search result to the provider.

Zero knowledge multi-party prescription management and drug interaction prevention system

Systems for cellular network authentication utilizing unlinkable anonymous credentials are disclosed. In embodiments, a computer program product is provided including a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a computing device to cause the computing device to: contact a mobile device network with a request to connect to the mobile device network; conduct an interactive credential issuance protocol with an Issuer of the mobile device network to generate an unlinkable anonymous credential; connect to the mobile device network based on a Verifier of the mobile device network verifying the computing device based on the unlinkable anonymous credential; and store a temporary mobile subscriber identity assigned to the mobile device by the mobile device network, wherein the temporary mobile subscriber identity is filled with a null value.

A device may capture one or more images. The device may automatically sort the one or more images into a save category and a delete category. The device may predict an action of a user towards the one or more images in the save category. The device may rank the one or more images in the save category based on the predicted action of the user. The device may display a first image to the user. The first image may have a highest rank among the one or more images in the save category.

Growing community of inventors

Austin, TX, United States of America

John F Behnken