Patents by Inventor Camilla OGURTSOVA

Camilla OGURTSOVA 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).

  • Identifying malicious executing code of an enclave
    Patent number: 10997289
    Abstract: Identifying malicious code execution of executing subject code of a software enclave of a processing system follows a process that includes monitoring performance characteristics of the processing system attributed to execution of the subject code of the software enclave. The monitoring produces performance data, which is stored to a relational database. The process applies a classification model to the stored performance data to obtain an output, and, based on the output of the classification model, identifies anomalous behavior in the execution of the subject code and determines a confidence level that the anomalous behavior exhibits malicious activity. Based on the confidence level exceeding a threshold, the process determines that the executing subject code is malicious and initiates halting of the execution of the subject code.
    Type: Grant
    Filed: May 21, 2018
    Date of Patent: May 4, 2021
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Juscelino Candido De Lima Junior, Breno H. Leitao, Camilla Ogurtsova, Marcel de Toledo Pineda
  • IDENTIFYING MALICIOUS EXECUTING CODE OF AN ENCLAVE
    Publication number: 20190354680
    Abstract: Identifying malicious code execution of executing subject code of a software enclave of a processing system follows a process that includes monitoring performance characteristics of the processing system attributed to execution of the subject code of the software enclave. The monitoring produces performance data, which is stored to a relational database. The process applies a classification model to the stored performance data to obtain an output, and, based on the output of the classification model, identifies anomalous behavior in the execution of the subject code and determines a confidence level that the anomalous behavior exhibits malicious activity. Based on the confidence level exceeding a threshold, the process determines that the executing subject code is malicious and initiates halting of the execution of the subject code.
    Type: Application
    Filed: May 21, 2018
    Publication date: November 21, 2019
    Inventors: Juscelino Candido DE LIMA JUNIOR, Breno H. LEITAO, Camilla OGURTSOVA, Marcel de Toledo PINEDA