Patents by Inventor Ghazaleh Beigi

Ghazaleh Beigi 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).

  • Systems and methods for utility-preserving deep reinforcement learning-based text anonymization
    Patent number: 11907666
    Abstract: Various embodiments of a system and associated method for anonymization of text without losing semantic utility of text by extracting a latent embedding representation of content with respect to a given task and by learning an optimal strategy for text embedding manipulation to satisfy both privacy and utility requirements are disclosed herein. In particular, the system balances private attribute obfuscation with retained semantic utility.
    Type: Grant
    Filed: November 16, 2021
    Date of Patent: February 20, 2024
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Ahmadreza Mosallanezhad, Ghazaleh Beigi, Huan Liu
  • Systems and methods for a privacy preserving text representation learning framework
    Patent number: 11763093
    Abstract: Various embodiments of a computer-implemented system which learns textual representations while filtering out potentially personally identifying data and retaining semantic meaning within the textual representations are disclosed herein.
    Type: Grant
    Filed: April 30, 2021
    Date of Patent: September 19, 2023
    Assignee: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Ghazaleh Beigi, Kai Shu, Ruocheng Guo, Suhang Wang, Huan Liu
  • SYSTEMS AND METHODS FOR UTILITY-PRESERVING DEEP REINFORCEMENT LEARNING-BASED TEXT ANONYMIZATION
    Publication number: 20220374606
    Abstract: Various embodiments of a system and associated method for anonymization of text without losing semantic utility of text by extracting a latent embedding representation of content with respect to a given task and by learning an optimal strategy for text embedding manipulation to satisfy both privacy and utility requirements are disclosed herein. In particular, the system balances private attribute obfuscation with retained semantic utility.
    Type: Application
    Filed: November 16, 2021
    Publication date: November 24, 2022
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Ahmadreza Mosallanezhad, Ghazaleh Beigi, Huan Liu
  • Privacy protection systems and methods
    Patent number: 11436371
    Abstract: Systems and methods of privacy protection of a user may include compiling an actual number of links in a web history corresponding to each topic in a plurality of internet topics; compiling a topic probability distribution based on the web history; determining an additional number of links to be added to each topic in the plurality of internet topics; and modifying the topic probability distribution by selecting a set of links corresponding to the additional number of links for each topic in the plurality of internet topics.
    Type: Grant
    Filed: February 5, 2020
    Date of Patent: September 6, 2022
    Assignee: Arizona Board of Regents on behalf of Arizona State University
    Inventors: Ghazaleh Beigi, Ruocheng Guo, Huan Liu, Yanchao Zhang, Alexander Nou
  • SYSTEMS AND METHODS FOR A PRIVACY PRESERVING TEXT REPRESENTATION LEARNING FRAMEWORK
    Publication number: 20210342546
    Abstract: Various embodiments of a computer-implemented system which learns textual representations while filtering out potentially personally identifying data and retaining semantic meaning within the textual representations are disclosed herein.
    Type: Application
    Filed: April 30, 2021
    Publication date: November 4, 2021
    Applicant: Arizona Board of Regents on Behalf of Arizona State University
    Inventors: Ghazaleh Beigi, Kai Shu, Ruocheng Guo, Suhang Wang, Huan Liu
  • PRIVACY PROTECTION SYSTEMS AND METHODS
    Publication number: 20210279369
    Abstract: Systems and methods of privacy protection of a user may include compiling an actual number of links in a web history corresponding to each topic in a plurality of internet topics; compiling a topic probability distribution based on the web history; determining an additional number of links to be added to each topic in the plurality of internet topics; and modifying the topic probability distribution by selecting a set of links corresponding to the additional number of links for each topic in the plurality of internet topics.
    Type: Application
    Filed: February 5, 2020
    Publication date: September 9, 2021
    Inventors: Ghazaleh Beigi, Ruocheng Guo, Huan Liu, Yanchao Zhang, Alexander Nou