Microsoft Technology Licensing, LLC

Dimensionalmechanics, Inc.

Hewlett-packard Development Company, L.p.

Rajeev Dutt

Gaurav S Anand

Kevin Michael Woley

Matthew Robert Ayers

Eric Fleischman

George Joy

Darren Louie

Jonathan Bradshaw

Jason K Ellis

A system and associated methods for the detection of anomalous behavior in a system. In some embodiments, time-series data that is obtained from the system (such as log data) may be used as an input to a process that converts the data into greyscale values. The greyscale values are used to construct an 'image' of the system operation that is used as an input to a convolutional neural network (CNN). The image is used to train the neural network so that the neural network is able to recognize when other input 'images' constructed from time-series data are anomalous or otherwise indicative of a difference between the prior (and presumed normal or acceptable) and the current operation of the system.

Systems and methods for detecting anomalous system or network behavior

Elements and processes used to enable the generation and interaction with complex networks, simulations, models, or environments. In some embodiments, this is accomplished by use of a client-server architecture that implements processes to improve data transport efficiency (and hence network usage), reduce latency experienced by users, and optimize the performance of the network, simulation, model or environment with respect to multiple parameters.

System, apparatus and methods for adaptive data transport and optimization of application execution

Systems and methods for creating entities that operate within a virtual environment, where in some embodiments the entities are substantially autonomous in the sense that they are capable of communications and interactions with the environment and other entities. In some embodiments, the entities may be capable of interacting with an environment other than the one in which they were created and originally configured. In some embodiments, the entities may engage in interactions with other entities that operate to enable changes in behavior of one or both of the entities.

System and methods for creating virtual environments

Various embodiments provide session-based filtering to filter messages in a cooperative manner between a client and a service provider. In at least some embodiments, a service provider can establish a messaging session with a client and deliver messages to the client. The client can implement various client-side techniques to filter some of the messages based on various client designated criteria. The service provider can obtain feedback from the client indicative of one or more of the delivered messages that have been filtered. The service provider can dynamically create a session-based list based on the feedback and use the list during the session to block messages on the server-side according to the client designated criteria. When the session concludes, the session-based list can be discarded. In this manner, message filtering can occur without persistent storage of state data for the filtering at the service provider.

Cooperative session-based filtering

This document describes various techniques for distributing credentials based on hardware profiles. A resource access request including a hardware profile is transmitted to a remote entity having access to a previous hardware profile and a credential useful to access a resource is received if at least a portion of the hardware profile matches the previous hardware profile.

Hardware-based credential distribution

Records of events associated with network entities in a network environment are received, where the network entities are selected from hardware entities, software entities, and combinations of hardware and software entities. The records of the events are identified to identify relationships between events associated with different ones of the network entities, where the records of the events identify corresponding network entities impacted by the events. A Bayesian network is constructed based on the analyzing, wherein the constructed Bayesian network is able to make predictions regarding relationships between events associated with the network elements.

Growing community of inventors

Redmond, WA, United States of America

Rajeev Dutt