Patents by Inventor Ali Anwar

Ali Anwar 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: 20220292387
    Abstract: Embodiments of the present disclosure include a federated learning method by a federated learning aggregator. The method may comprise creating a log of previously provided gradients from a plurality of workers, receiving updated gradients from the plurality of workers, calculating a vulnerability weight for each layer of a global machine learning model using the updated gradients, calculating an aggregated gradient using the vulnerability weight and the updated gradients, and updating the global machine learning model using the aggregated gradient. Some embodiments may also determine whether a Byzantine attack is occurring based upon the calculated aggregated gradient.
    Type: Application
    Filed: March 9, 2021
    Publication date: September 15, 2022
    Inventors: Yi Zhou, Nathalie Baracaldo Angel, Kamala Micaela Noelle Varma, Ali Anwar, Syed Amer Zawad
  • Publication number: 20220292392
    Abstract: An indication of availability over time and resource usage is maintained for each computing device of a plurality of computing devices. An optimal combination of a subset of the plurality of computing devices is determined for each round of one or more rounds of training based on the availability over time and the resource usage for each computing device. A global model is generated utilizing the one or more optimal combinations of the plurality of computing devices and a query is performed utilizing the global model.
    Type: Application
    Filed: March 11, 2021
    Publication date: September 15, 2022
    Inventors: Ali Anwar, Syed Amer Zawad, Yi Zhou, NATHALIE BARACALDO ANGEL
  • Publication number: 20220083904
    Abstract: A method, a computer system, and a computer program product are provided for federated learning enhanced with semantic learning. An aggregator may receive cluster information from distributed computing devices. The cluster information may relate to identified clusters in sample data of the distributed computing devices. The aggregator may integrate the cluster information to define classes. The integrating may include identifying any redundant clusters amongst the identified clusters. A number of the classes may correspond to a total number of the clusters from the distributed computing devices reduced by any redundant clusters. A deep learning model may be sent from the aggregator to the distributed computing devices. The deep learning model may include an output layer having nodes that may correspond to the defined classes. The aggregator may receive results of federated learning performed by the distributed computing devices. The federated learning may train the deep learning model.
    Type: Application
    Filed: September 16, 2020
    Publication date: March 17, 2022
    Inventors: Vito Paolo Pastore, Yi Zhou, Nathalie Baracaldo Angel, Ali Anwar, Simone Bianco
  • Publication number: 20210409197
    Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.
    Type: Application
    Filed: September 13, 2021
    Publication date: December 30, 2021
    Inventors: Nathalie Baracaldo Angel, Stacey Truex, Heiko H. Ludwig, Ali Anwar, Thomas Steinke, Rui Zhang
  • Patent number: 11139961
    Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.
    Type: Grant
    Filed: May 7, 2019
    Date of Patent: October 5, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nathalie Baracaldo Angel, Stacey Truex, Heiko H. Ludwig, Ali Anwar, Thomas Steinke, Rui Zhang
  • Publication number: 20210304062
    Abstract: One embodiment provides a method for federated learning across a plurality of data parties, comprising assigning each data party with a corresponding namespace in an object store, assigning a shared namespace in the object store, and triggering a round of federated learning by issuing a customized learning request to at least one data party. Each customized learning request issued to a data party triggers the data party to locally train a model based on training data owned by the data party and model parameters stored in the shared namespace, and upload a local model resulting from the local training to a corresponding namespace in the object store the data party is assigned with. The method further comprises retrieving, from the object store, local models uploaded to the object store during the round of federated learning, and aggregating the local models to obtain a shared model.
    Type: Application
    Filed: March 27, 2020
    Publication date: September 30, 2021
    Inventors: Shashank Rajamoni, Ali Anwar, Yi Zhou, Heiko H. Ludwig, Nathalie Baracaldo Angel
  • Patent number: 11132210
    Abstract: A computer-implemented method includes receiving characteristics of available resources usable for downloading layers of a container image and fetching a manifest of the container image from a container registry. The method includes determining layers of the container image to be downloaded based on the manifest and, based on the characteristics of the available resources and sizes of the layers to be downloaded, adjusting an optimal parallelism to download the layers. The method includes downloading the layers.
    Type: Grant
    Filed: May 9, 2019
    Date of Patent: September 28, 2021
    Assignee: International Business Machines Corporation
    Inventors: Ali Anwar, Mohamed Mohamed, Samir Tata, Heiko H. Ludwig
  • Publication number: 20210287114
    Abstract: Techniques for improved federated learning are provided. One or more queries are issued to a plurality of participants in a federated learning system, and one or more replies are received from the plurality of participants. A first aggregated model is generated based on the one or more relies and a first influence vector. Upon determining that a predefined criterion is satisfied, a second influence vector modifying a weight of a first participant of the plurality of participants is generated. A second aggregated model is generated based on the one or more replies and the second influence vector.
    Type: Application
    Filed: March 13, 2020
    Publication date: September 16, 2021
    Inventors: Yi ZHOU, Ali ANWAR, Nathalie BARACALDO ANGEL, Hekio H. LUDWIG
  • Publication number: 20210174243
    Abstract: Systems and techniques that facilitate universal and efficient privacy-preserving vertical federated learning are provided. In various embodiments, a key distribution component can distribute respective feature-dimension public keys and respective sample-dimension public keys to respective participants in a vertical federated learning framework governed by a coordinator, wherein the respective participants can send to the coordinator respective local model updates encrypted by the respective feature-dimension public keys and respective local datasets encrypted by the respective sample-dimension public keys. In various embodiments, an inference prevention component can verify a participant-related weight vector generated by the coordinator, based on which the key distribution component can distribute to the coordinator a functional feature-dimension secret key that can aggregate the encrypted respective local model updates into a sample-related weight vector.
    Type: Application
    Filed: December 6, 2019
    Publication date: June 10, 2021
    Inventors: Nathalie Baracaldo Angel, Runhua Xu, Yi Zhou, Ali Anwar, Heiko H. Ludwig
  • Publication number: 20210143987
    Abstract: Techniques for federated learning are provided. A plurality of public encryption keys are distributed to a plurality of participants in a federated learning system, and a first plurality of responses is received from the plurality of participants, where each respective response of the first plurality of responses was generated based on training data local to a respective participant of the plurality of participants and is encrypted using a respective public encryption key of the plurality of public encryption keys. A first aggregation vector is generated based on the first plurality of responses, and a first private encryption key is retrieved using the first aggregation vector. An aggregated model is then generated based on the first private encryption key and the first plurality of responses.
    Type: Application
    Filed: November 13, 2019
    Publication date: May 13, 2021
    Inventors: Runhua XU, Nathalie BARACALDO ANGEL, Yi ZHOU, Ali ANWAR, Heiko H LUDWIG
  • Publication number: 20200412743
    Abstract: Systems, computer-implemented methods, and computer program products that can facilitate detection of an adversarial backdoor attack on a trained model at inference time are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a log component that records predictions and corresponding activation values generated by a trained model based on inference requests. The computer executable components can further comprise an analysis component that employs a model at an inference time to detect a backdoor trigger request based on the predictions and the corresponding activation values. In some embodiments, the log component records the predictions and the corresponding activation values from one or more layers of the trained model.
    Type: Application
    Filed: June 25, 2019
    Publication date: December 31, 2020
    Inventors: Nathalie Baracaldo Angel, Yi Zhou, Bryant Chen, Ali Anwar, Heiko H. Ludwig
  • Publication number: 20200364608
    Abstract: A computer-implemented method of communicating in a federated learning environment includes an aggregator and a plurality of federated learning participants that respectively maintain their own data and communicate with the aggregator. The aggregator monitors the plurality of federated learning participants for factors associated with stragglers. The federated learning participants are assigned into tiers based on the monitoring of the factors. The aggregator queries the federated learning participants in a selected tier and designates late responders as stragglers. Maximum waiting time may be defined for each tier. The aggregator applies a predicted response for drop outs including collected participants' replies and computed predictions associated with the stragglers to update a training of a federated learning model. The federated learning participants that do not respond within the designated wait time are designated as drop outs.
    Type: Application
    Filed: May 13, 2019
    Publication date: November 19, 2020
    Inventors: Ali Anwar, Yi Zhou, Nathalie Baracaldo Angel, Heiko H. Ludwig
  • Publication number: 20200358599
    Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.
    Type: Application
    Filed: May 7, 2019
    Publication date: November 12, 2020
    Inventors: Nathalie Baracaldo Angel, Stacey Truex, Heiko H. Ludwig, Ali Anwar, Thomas Steinke, Rui Zhang
  • Publication number: 20200356387
    Abstract: A computer-implemented method includes receiving characteristics of available resources usable for downloading layers of a container image and fetching a manifest of the container image from a container registry. The method includes determining layers of the container image to be downloaded based on the manifest and, based on the characteristics of the available resources and sizes of the layers to be downloaded, adjusting an optimal parallelism to download the layers. The method includes downloading the layers.
    Type: Application
    Filed: May 9, 2019
    Publication date: November 12, 2020
    Inventors: Ali Anwar, Mohamed Mohamed, Samir Tata, Heiko H. Ludwig
  • Patent number: 10467036
    Abstract: Systems and methods are provided for dynamic metering adjustment for service management of a computing platform. For example, a plurality of virtual machines are provisioned across a plurality of computing nodes of a computing platform. Data samples are collected for a metric that is monitored with regard to resource utilization in the computing platform by the virtual machines. The data samples are initially collected at a predefined sampling frequency. The data samples collected over time for the metric are analyzed to determine an amount of deviation in values of the collected data samples. A new sampling frequency is determined for collecting data samples for the metric based on the determined amount of deviation. The new sampling frequency is applied to collect data samples for the metric, wherein the new sampling frequency is less than the predefined sampling frequency.
    Type: Grant
    Filed: October 29, 2015
    Date of Patent: November 5, 2019
    Assignee: International Business Machines Corporation
    Inventors: Ali Anwar, Andrzej Kochut, Anca Sailer, Charles O. Schulz, Alla Segal
  • Patent number: 10171371
    Abstract: Systems and methods are provided to support service management in cloud computing networks. For example, a method for managing a computing platform includes provisioning a plurality of virtual machines across a plurality of computing nodes of a computing platform, wherein the provisioned virtual machines are configured to execute service workloads to provide one or more services to customers, and utilizing one or more of the provisioned virtual machines which execute the service workloads to further perform service management operations for managing the computing platform. The service management operations for managing the computing platform include, e.g., mediation and rating operations for revenue management of the computing platform.
    Type: Grant
    Filed: September 30, 2015
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: Ali Anwar, Salman A. Baset, Andrzej P. Kochut, Hui Lei, Anca Sailer, Alla Segal
  • Publication number: 20160094410
    Abstract: Systems and methods are provided to support service management in cloud computing networks. For example, a method for managing a computing platform includes provisioning a plurality of virtual machines across a plurality of computing nodes of a computing platform, wherein the provisioned virtual machines are configured to execute service workloads to provide one or more services to customers, and utilizing one or more of the provisioned virtual machines which execute the service workloads to further perform service management operations for managing the computing platform. The service management operations for managing the computing platform include, e.g., mediation and rating operations for revenue management of the computing platform.
    Type: Application
    Filed: September 30, 2015
    Publication date: March 31, 2016
    Inventors: Ali Anwar, Salman A. Baset, Andrzej P. Kochut, Hui Lei, Anca Sailer, Alla Segal
  • Publication number: 20160094401
    Abstract: Systems and methods are provided for dynamic metering adjustment for service management of a computing platform. For example, a plurality of virtual machines are provisioned across a plurality of computing nodes of a computing platform. Data samples are collected for a metric that is monitored with regard to resource utilization in the computing platform by the virtual machines. The data samples are initially collected at a predefined sampling frequency. The data samples collected over time for the metric are analyzed to determine an amount of deviation in values of the collected data samples. A new sampling frequency is determined for collecting data samples for the metric based on the determined amount of deviation. The new sampling frequency is applied to collect data samples for the metric, wherein the new sampling frequency is less than the predefined sampling frequency.
    Type: Application
    Filed: October 29, 2015
    Publication date: March 31, 2016
    Inventors: Ali Anwar, Andrzej Kochut, Anca Sailer, Charles O. Schulz, Alla Segal
  • Patent number: 8745480
    Abstract: An on-demand hyperlink computer search tool implements a method of providing hyperlinked search results that overlay a computer document. The method includes selecting an object in a computer document, submitting the object to a search engine, receiving results, categorizing the results as clusters and displaying the clusters. The clusters are displayed in layers on the same page as the computer document and over the object. Furthermore, an “additional object” may be selected from the clusters. If the selected “additional object” hyperlinks to a specific website, the website is retrieved. If not, the method repeats the process iteratively until “another additional object” that is selected hyperlinks to a specific website.
    Type: Grant
    Filed: September 20, 2007
    Date of Patent: June 3, 2014
    Inventor: Arman Ali Anwar
  • Publication number: 20080072179
    Abstract: An on-demand hyperlink computer search tool implements a method of providing hyperlinked search results that overlay a computer document. The method includes selecting an object in a computer document, submitting the object to a search engine, receiving results, categorizing the results as clusters and displaying the clusters. The clusters are displayed in layers on the same page as the computer document and over the object. Furthermore, an “additional object” may be selected from the clusters. If the selected “additional object” hyperlinks to a specific website, the website is retrieved. If not, the method repeats the process iteratively until “another additional object” that is selected hyperlinks to a specific website.
    Type: Application
    Filed: September 20, 2007
    Publication date: March 20, 2008
    Inventor: Arman Ali Anwar