Patents by Inventor Ji Hyeon YU

Ji Hyeon YU 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: 20240229096
    Abstract: Provided are a composition for expressing and/or producing a polypeptide of interest in an animal cell, comprising a target-specific endonuclease system or an encoding gene thereof and a donor DNA structure; a recombinant animal cell into which said composition is introduced and a manufacturing method thereof; and a method for expressing and/or producing a polypeptide of interest in an animal cell, comprising a step of introducing said composition into the animal cell and/or a step of culturing said animal cell.
    Type: Application
    Filed: October 12, 2018
    Publication date: July 11, 2024
    Inventors: Sang Su BAE, Jae Sung WOO, Ji Hyeon YU
  • Patent number: 11797688
    Abstract: An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result.
    Type: Grant
    Filed: May 26, 2021
    Date of Patent: October 24, 2023
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Joo Beom Yun, Ji Hyeon Yu, Hyun Jun Mun
  • Publication number: 20220019675
    Abstract: An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result.
    Type: Application
    Filed: May 26, 2021
    Publication date: January 20, 2022
    Inventors: Joo Beom YUN, Ji Hyeon YU, Hyun Jun MUN