Microsoft Technology Licensing, LLC

Christopher Barnes

Frank Byrum

Edward Thomas Banti

James R Knibb

Palash Biswas

Mayerber L Carvalho Neto

Mayank Mehta

Nagaraju Palla

Kiran Nallabothula

Nagaraj Patil

Ayse Yesim Koman

Mayerber Loureiro De Carvalho Neto

Victor William Habib Boctor

Wilson Li

Jonathan LeCroy

Victor Boctor

Hao Zhang

Gregory Kostal

Amit Fulay

Vladimir Yarmolenko

Krassimir Emilov Karamfilov

Chandresh Kumar Jain

Michael Nelte

Yuhui Zhong

Pankaj Mohan Kamat

Tejas Patel

A computing system receives decrypts learned parameters of a computer-implemented predictive model stored in a computer-readable, non-volatile data store upon instantiation of a model process in volatile memory of the computing system. The predictive model is parameterized by learned parameters that are based upon private data of a user, wherein the learned parameters of the predictive model have been encrypted subsequent to training of the predictive model based upon the private data of the user. The computing system receives a request for a prediction associated with the user. Upon authorizing the request, the computing identifies the predictive model. The computing system, by way of the model process, generates the prediction based upon the request and the predictive model. The computing system outputs the prediction to a computing device associated with the user.

System for content encryption for predictive models trained on private data

Historical telemetry data can be used to generate predictions for various classes of data at various aggregates of a system that implements an online service. An anomaly detection process can then be utilized to detect anomalies for a class of data at a selected aggregate. An example anomaly detection process includes receiving telemetry data originating from a plurality of client devices, selecting a class of data from the telemetry data, converting the class of data to a set of metrics, aggregating the set of metrics according to a component of interest to obtain values of aggregated metrics over time for the component of interest, determining a prediction error by comparing the values of the aggregated metrics to a prediction, detecting an anomaly based at least in part on the prediction error, and transmitting an alert message of the anomaly to a receiving entity.

Anomaly detection and classification using telemetry data

Architecture that employs encryption and storage of encryption keys to protect trusted client message content from an untrusted third-party hosted service. Each trusted user machine is configured to optionally apply security to messages. Rules determine when automatic protection is applied and the level of protection to apply. The trusted client automatically downloads the rules (or rules policies) from a trusted rules service and caches the rules locally. During composition, the rules analyze the message and automatically apply security template(s) to the message. The security template(s) encrypt the body of the message, but not the headers or subject. The untrusted message service processes the header and delivers the message to the correct recipient. The hosted service cannot view the contents of the message body, and only intended recipients of the protected message can view the message body. Offline protection is supported, and the user can override protection by the rules.

Protecting content from third party using client-side security protection

A hosting provider operates a server system that provides a service to one or more tenants. The server system receives configuration data from the tenants. As part of providing the service to a given tenant, the server system attempts to access an external service due to the configuration data received from the given tenant identifying the external service. Service access errors can occur when attempting to access the external service. In response to determining that an error has occurred when attempting to access the external service, the server system sends a service access alert to a recipient associated with the given tenant. The service access alert notifies the recipient that the error has occurred.

Alerting recipients to errors occurring when accessing external services

Business to business secure mail may be provided. Consistent with embodiments of the invention, a protected message may be received. The recipient may request a token from a trust broker, submit the token to an authorization server associated with the sender, receive a user license from the authorization server; and decrypt the protected message using the user license. The protected message may restrict actions that may be taken by the recipient, such as forwarding to other users.

Business to business secure mail

Growing community of inventors

Redmond, WA, United States of America

Christopher Barnes