Patents by Inventor Kristina Lerman

Kristina Lerman 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 a text mining approach for predicting exploitation of vulnerabilities
    Patent number: 11520900
    Abstract: Various embodiments of a computer-implemented framework for predicting exploitation of software vulnerabilities are disclosed.
    Type: Grant
    Filed: August 22, 2019
    Date of Patent: December 6, 2022
    Assignees: Arizona Board of Regents on Behalf of Arizona State University, University of Southern California
    Inventors: Nazgol Tavabi, Palash Goyal, Kristina Lerman, Mohammed Almukaynizi, Paulo Shakarian
  • SYSTEMS AND METHODS FOR A TEXT MINING APPROACH FOR PREDICTING EXPLOITATION OF VULNERABILITIES
    Publication number: 20220229912
    Abstract: Various embodiments of a computer-implemented framework for predicting exploitation of software vulnerabilities are disclosed.
    Type: Application
    Filed: August 22, 2019
    Publication date: July 21, 2022
    Applicants: Arizona Board of Regents on Behalf of Arizona State University, University of Southern California
    Inventors: Nazgol Tavabi, Palash Goyal, Kristina Lerman, Mohammed Almukaynizi, Paulo Shakarian
  • TECHNIQUES TO EVALUATE AND ENHANCE COGNITIVE PERFORMANCE
    Publication number: 20170042461
    Abstract: In one embodiment of the present application, an operator provides entries into the computer workstation indicative of an evaluation. Assessment of the entries takes place relative to data representative of a corresponding multiple resource neuroenergetic model for the cognitively demanding activity. Generation of an operator instruction results from the assessment that is provided to the operator through the computer workstation. The operator instruction directs the operator to take a break from the cognitively demanding activity based on the assessment.
    Type: Application
    Filed: July 15, 2016
    Publication date: February 16, 2017
    Applicant: BATTELLE MEMORIAL INSTITUTE
    Inventors: Nathan O. Hodas, Kristina Lerman, Lyndsey Franklin, Dustin Arendt
  • Learning data prototypes for information extraction
    Patent number: 6714941
    Abstract: A method for determining statistically significant token sequences lends itself for use in the recognition of broken wrappers as well as the construction of new wrapper rules. When new wrapper rules are needed as the underlying wrapped data has changed, training examples are used to recognized data rule candidates that are culled with a bias for rule candidates that would be probably more successful. The resulting rule candidate set is clustered according to feature characteristics, then compared to the training examples. Those rule candidates most similar to the training examples are used to create new wrapper rules.
    Type: Grant
    Filed: July 19, 2000
    Date of Patent: March 30, 2004
    Assignee: University of Southern California
    Inventors: Kristina Lerman, Steven Minton