公开(公告)号：US20240256922A1

公开(公告)日：2024-08-01

申请号：US18104073

申请日：2023-01-31

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ganesh ANANTHANARAYANAN ,  Yuanchao SHU

IPC: G06N5/04 ,  G16Y20/10 ,  G16Y30/00

CPC classification number: G06N5/04 ,  G16Y20/10 ,  G16Y30/00

Abstract: Systems and methods are provided for dynamically adapting configuration setting associated with capturing content as input data for inferencing in the Multi-Access Edge Computing in a 5G telecommunication network. The inferencing is based on a use of a deep neural network. In particular, the method includes determining a gradient of a change in inference data over a change in configuration setting for capturing input data (the inference-configuration gradient). The method further updates the configuration setting based on the gradient of a change in inference data over a change in the configuration setting. The inference-configuration gradient is based on a combination of an input-configuration gradient and an inference-input gradient. The input-configuration gradient indicates a change in input data as the configuration setting value changes. The inference-input gradient indicates, as a saliency of the deep neural network, a change in inference result of the input data as the input data changes.

公开(公告)号：US20240171391A1

公开(公告)日：2024-05-23

申请号：US17990646

申请日：2022-11-18

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Ganesh ANANTHANARAYANAN ,  Ramarathnam VENKATESAN ,  Yuanchao SHU ,  Kiran MUTHABATULLA ,  Yoganand RAJASEKARAN

IPC: H04L9/08 ,  H04L9/14

CPC classification number: H04L9/0897 ,  H04L9/0822 ,  H04L9/14 ,  H04L2209/80

Abstract: The techniques described herein use an edge device to manage the security for a data stream being ingested by a tenant and a cloud platform. The creation of the data stream for ingestion occurs in an environment that is trusted by a tenant (e.g., an on-premises enterprise network). The cloud platform that is part of the data stream ingestion process is outside this trusted environment, and thus, the tenant loses an element of security when ingesting data streams for cloud storage and/or cloud processing. Accordingly, the edge device is configured on a trust boundary so that the data stream ingestion process associated with a cloud platform is secured, or trusted by the tenant. The edge device is configured to encrypt the data stream using a data encryption key and/or manage the protection of the data encryption key.

公开(公告)号：US20240121081A1

公开(公告)日：2024-04-11

申请号：US18045335

申请日：2022-10-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ramarathnam VENKATESAN ,  Nishanth CHANDRAN ,  Ganesh ANANTHANARAYANAN ,  Panagiotis ANTONOPOULOS ,  Srinath T.V. SETTY ,  Daniel John CARROLL, JR. ,  Kiran MUTHABATULLA ,  Yuanchao SHU ,  Sanjeev MEHROTRA

IPC: H04L9/08

CPC classification number: H04L9/0825 ,  H04L9/085 ,  H04L9/0866

Abstract: An access control system is disclosed for controlling access to a resource. A request is received by a location attribute policy (LAP) server to access an encrypted resource. The LAP server accesses a resource policy that identifies requirements for granting access to the encrypted resource, such as a list of attributes of the requestor that are required and a dynamic attribute requirement of the requestor. The LAP server receives a cryptographic proof from the computing device that the requestor possesses the attributes and validates the proof based at least on information obtained from a trusted ledger. Once the proof is validated, the LAP server provides a shared secret associated with the dynamic attribute requirement to a decryption algorithm. The decryption algorithm uses the dynamic attribute shared secret in combination with one or more attribute shared secrets from the requestor to generate a decryption key for the encrypted resource.

公开(公告)号：US20220414534A1

公开(公告)日：2022-12-29

申请号：US17362115

申请日：2021-06-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ganesh ANANTHANARAYANAN ,  Yuanchao SHU ,  Paramvir BAHL ,  Tsuwang HSIEH

IPC: G06N20/00

Abstract: Systems and methods are provided for continuous learning of models across hierarchies under a multi-access edge computing. In particular, an on-premises edge server, using a model, generates inference data associated with captured stream data. A data drift determiner determines a data drift in the inference data by comparing the data against reference data generated using a golden model. The data drift indicates a loss of accuracy in the inference data. A gateway model maintains one or more models in a model cache for update the model. The gateway model instructs the one or more servers to train the new model. The gateway model transmits the trained model to update the model in the on-premises edge server. Training the new model includes determining an on-premises edge server with computing resources available to train the new model while generating other inference data for incoming stream data in the data analytic pipeline.

公开(公告)号：US20220188569A1

公开(公告)日：2022-06-16

申请号：US17124172

申请日：2020-12-16

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ganesh ANANTHANARAYANAN ,  Yuanchao SHU ,  Tsu-wang HSIEH ,  Nikolaos KARIANAKIS ,  Paramvir BAHL ,  Romil BHARDWAJ

IPC: G06K9/62 ,  G06F9/50 ,  G06N20/00 ,  G06K9/00

Abstract: Examples are disclosed that relate to methods and computing devices for allocating computing resources and selecting hyperparameter configurations during continuous retraining and operation of a machine learning model. In one example, a computing device configured to be located at a network edge between a local network and a cloud service comprises a processor and a memory storing instructions executable by the processor to operate a machine learning model. During a retraining window, a selected portion of a video stream is selected for labeling. At least a portion of a labeled retraining data set is selected for profiling a superset of hyperparameter configurations. For each configuration of the superset of hyperparameter configurations, a profiling test is performed. The profiling test is terminated, and a change in inference accuracy that resulted from the profiling test is extrapolated. Based upon the extrapolated inference accuracies, a set of selected hyperparameter configurations is output.