Patents by Inventor Micah Sheller

Micah Sheller 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).

  • Publication number: 20250061229
    Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.
    Type: Application
    Filed: November 6, 2024
    Publication date: February 20, 2025
    Applicant: Intel Corporation
    Inventors: Micah Sheller, Cory Cornelius
  • Patent number: 12223079
    Abstract: A method comprises receiving in a governor device, from a plurality of data owner devices, metadata for one or more datasets maintained by the plurality of data owner devices, registering the metadata for the one or more datasets with the governor device, in response to a request from an aggregator, providing at least a portion of the metadata for the one or more datasets to the aggregator, receiving, from the aggregator, a compute plan to be implemented by the plurality of data owner devices, distributing at least a portion of the compute plan to the plurality of data owner devices, in response to receiving, from the plurality of data owner devices, a verification report and a certification for an enclave, binding the enclave to a host device, and providing the compute plan to the plurality of data owner devices.
    Type: Grant
    Filed: September 23, 2021
    Date of Patent: February 11, 2025
    Assignee: INTEL CORPORATION
    Inventors: Prakash Narayana Moorthy, Patrick Foley, Micah Sheller, Clair Bowman, G. Anthony Reina, Jason Martin, Shih-Han Wang
  • Patent number: 12169584
    Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.
    Type: Grant
    Filed: November 28, 2022
    Date of Patent: December 17, 2024
    Assignee: Intel Corporation
    Inventors: Micah Sheller, Cory Cornelius
  • Publication number: 20240211549
    Abstract: An example apparatus includes interface circuitry, machine-readable instructions, and at least one processor circuit to be programmed by the machine-readable instructions to access a first set of samples associated with a diffusion model, the first set of samples including a plurality of input data samples, generate a representation of the first set of samples, sample the representation of the first set of samples to generate a representation of a second set of samples, and generate the second set of samples from the representation of the second set of samples, the second set of samples including a plurality of output data samples, an output data sample corresponding to an input data sample and being different from the corresponding input data sample.
    Type: Application
    Filed: February 29, 2024
    Publication date: June 27, 2024
    Inventors: Marius Arvinte, Brandon Edwards, Cory Cornelius, Jason Martin, Sebastian Szyller, Micah Sheller, Nageen Himayat
  • Publication number: 20230205918
    Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.
    Type: Application
    Filed: November 28, 2022
    Publication date: June 29, 2023
    Inventors: Micah Sheller, Cory Cornelius
  • Patent number: 11657162
    Abstract: In one example an apparatus comprises a memory and a processor to create, from a first deep neural network (DNN) model, a first plurality of DNN models, generate a first set of adversarial examples that are misclassified by the first plurality of deep neural network (DNN) models, determine a first set of activation path differentials between the first plurality of adversarial examples, generate, from the first set of activation path differentials, at least one composite adversarial example which incorporates at least one intersecting critical path that is shared between at least two adversarial examples in the first set of adversarial examples, and use the at least one composite adversarial example to generate a set of inputs for a subsequent training iteration of the DNN model. Other examples may be described.
    Type: Grant
    Filed: March 22, 2019
    Date of Patent: May 23, 2023
    Assignee: INTEL CORPORATION
    Inventors: Michael Kounavis, Antonios Papadimitriou, Anindya Sankar Paul, Micah Sheller, Li Chen, Cory Cornelius, Brandon Edwards
  • Patent number: 11556730
    Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.
    Type: Grant
    Filed: March 30, 2018
    Date of Patent: January 17, 2023
    Assignee: Intel Corporation
    Inventors: Micah Sheller, Cory Cornelius
  • Patent number: 11526745
    Abstract: Methods, apparatus, systems and articles of manufacture for federated training of a neural network using trusted edge devices are disclosed. An example system includes an aggregator device to aggregate model updates provided by one or more edge devices. The one or more edge devices to implement respective neural networks, and provide the model updates to the aggregator device. At least one of the edge devices to implement the neural network within a trusted execution environment.
    Type: Grant
    Filed: February 8, 2018
    Date of Patent: December 13, 2022
    Assignee: Intel Corporation
    Inventors: Micah Sheller, Cory Cornelius, Jason Martin, Yonghong Huang, Shih-Han Wang
  • Patent number: 11501001
    Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.
    Type: Grant
    Filed: June 24, 2020
    Date of Patent: November 15, 2022
    Assignee: INTEL CORPORATION
    Inventors: Shih-Han Wang, Yonghong Huang, Micah Sheller, Cory Cornelius
  • Publication number: 20220012355
    Abstract: A method comprises receiving in a governor device, from a plurality of data owner devices, metadata for one or more datasets maintained by the plurality of data owner devices, registering the metadata for the one or more datasets with the governor device, in response to a request from an aggregator, providing at least a portion of the metadata for the one or more datasets to the aggregator, receiving, from the aggregator, a compute plan to be implemented by the plurality of data owner devices, distributing at least a portion of the compute plan to the plurality of data owner devices, in response to receiving, from the plurality of data owner devices, a verification report and a certification for an enclave, binding the enclave to a host device, and providing the compute plan to the plurality of data owner devices.
    Type: Application
    Filed: September 23, 2021
    Publication date: January 13, 2022
    Applicant: Intel Corporation
    Inventors: Prakash Narayana Moorthy, Patrick Foley, Micah Sheller, Clair Bowman, G. Anthony Reina, Jason Martin, Shih-Han Wang
  • Publication number: 20210374247
    Abstract: The present invention discloses a secure ML pipeline to improve the robustness of ML models against poisoning attacks and utilizing data provenance as a tool. Two components are added to the ML pipeline, a data quality pre-processor, which filters out untrusted training data based on provenance derived features and an audit post-processor, which localizes the malicious source based on training dataset analysis using data provenance.
    Type: Application
    Filed: August 10, 2021
    Publication date: December 2, 2021
    Applicant: Intel Corporation
    Inventors: Salmin Sultana, Lawrence Booth, JR., Mic Bowman, Jason Martin, Micah Sheller
  • Publication number: 20200327238
    Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.
    Type: Application
    Filed: June 24, 2020
    Publication date: October 15, 2020
    Applicant: INTEL CORPORATION
    Inventors: Shih-Han Wang, Yonghong Huang, Micah Sheller, Cory Cornelius
  • Patent number: 10726134
    Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.
    Type: Grant
    Filed: August 14, 2018
    Date of Patent: July 28, 2020
    Assignee: INTEL CORPORATION
    Inventors: Shih-Han Wang, Yonghong Huang, Micah Sheller, Cory Cornelius
  • Publication number: 20190220605
    Abstract: In one example an apparatus comprises a memory and a processor to create, from a first deep neural network (DNN) model, a first plurality of DNN models, generate a first set of adversarial examples that are misclassified by the first plurality of deep neural network (DNN) models, determine a first set of activation path differentials between the first plurality of adversarial examples, generate, from the first set of activation path differentials, at least one composite adversarial example which incorporates at least one intersecting critical path that is shared between at least two adversarial examples in the first set of adversarial examples, and use the at least one composite adversarial example to generate a set of inputs for a subsequent training iteration of the DNN model. Other examples may be described.
    Type: Application
    Filed: March 22, 2019
    Publication date: July 18, 2019
    Applicant: Intel Corporation
    Inventors: Michael Kounavis, Antonios Papadimitriou, Anindya Paul, Micah Sheller, Li Chen, Cory Cornelius, Brandon Edwards
  • Publication number: 20190042878
    Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.
    Type: Application
    Filed: March 30, 2018
    Publication date: February 7, 2019
    Inventors: Micah Sheller, Cory Cornelius
  • Publication number: 20190042761
    Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.
    Type: Application
    Filed: August 14, 2018
    Publication date: February 7, 2019
    Inventors: Shih-Han Wang, Yonghong Huang, Micah Sheller, Cory Cornelius
  • Publication number: 20190042937
    Abstract: Methods, apparatus, systems and articles of manufacture for federated training of a neural network using trusted edge devices are disclosed. An example system includes an aggregator device to aggregate model updates provided by one or more edge devices. The one or more edge devices to implement respective neural networks, and provide the model updates to the aggregator device. At least one of the edge devices to implement the neural network within a trusted execution environment.
    Type: Application
    Filed: February 8, 2018
    Publication date: February 7, 2019
    Inventors: Micah Sheller, Cory Cornelius, Jason Martin, Yonghong Huang, Shih-Han Wang
  • Patent number: 9762566
    Abstract: Technologies are provided in embodiments to manage an authentication confirmation score. Embodiments are configured to identify, in absolute session time, a beginning time and an ending time of an interval of an active user session on a client. Embodiments are also configured to determine a first value representing a first subset of a set of prior user sessions, where the prior user sessions of the first subset were active for at least as long as the beginning time. Embodiments can also determine a second value representing a second subset of the set of prior user sessions, where the prior user sessions of the second subset were active for at least as long as the ending time. Embodiments also determine, based on the first and second values, a decay rate for the authentication confidence score of the active user session. In some embodiments, the set is based on context attributes.
    Type: Grant
    Filed: January 30, 2017
    Date of Patent: September 12, 2017
    Assignee: Intel Corporation
    Inventors: Micah Sheller, Conor Cahill, Jason Martin, Brandon Baker
  • Publication number: 20170142089
    Abstract: Technologies are provided in embodiments to manage an authentication confirmation score. Embodiments are configured to identify, in absolute session time, a beginning time and an ending time of an interval of an active user session on a client. Embodiments are also configured to determine a first value representing a first subset of a set of prior user sessions, where the prior user sessions of the first subset were active for at least as long as the beginning time. Embodiments can also determine a second value representing a second subset of the set of prior user sessions, where the prior user sessions of the second subset were active for at least as long as the ending time. Embodiments also determine, based on the first and second values, a decay rate for the authentication confidence score of the active user session. In some embodiments, the set is based on context attributes.
    Type: Application
    Filed: January 30, 2017
    Publication date: May 18, 2017
    Applicant: Intel Corporation
    Inventors: Micah Sheller, Conor Cahill, Jason Martin, Brandon Baker
  • Patent number: 9590966
    Abstract: Technologies are provided in embodiments to manage an authentication confirmation score. Embodiments are configured to identify, in absolute session time, a beginning time and an ending time of an interval of an active user session on a client. Embodiments are also configured to determine a first value representing a first subset of a set of prior user sessions, where the prior user sessions of the first subset were active for at least as long as the beginning time. Embodiments can also determine a second value representing a second subset of the set of prior user sessions, where the prior user sessions of the second subset were active for at least as long as the ending time. Embodiments also determine, based on the first and second values, a decay rate for the authentication confidence score of the active user session. In some embodiments, the set is based on context attributes.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: March 7, 2017
    Assignee: Intel Corporation
    Inventors: Micah Sheller, Conor Cahill, Jason Martin, Brandon Baker