Patents by Inventor Julien Piet

Julien Piet 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: 20220345382
    Abstract: A system and method for traffic classification using snippets and on-the-fly traffic classifiers can build traffic classifiers that leverage interpretable feature sets without the need to inspect payloads—ensuring functionality across clear-text and encrypted flows. In one embodiment, the system identifies n-grams (“snippets”) in a network flow's sequence-of-message-lengths that are strongly indicative of a given class of traffic and predicts a network flow's class by assessing the presence of snippets relevant to different classes.
    Type: Application
    Filed: October 7, 2021
    Publication date: October 27, 2022
    Applicant: CORELIGHT, INC.
    Inventor: Julien Piet
  • Patent number: 11463334
    Abstract: A system and method for traffic classification using snippets and on-the-fly traffic classifiers can build traffic classifiers that leverage interpretable feature sets without the need to inspect payloads—ensuring functionality across clear-text and encrypted flows. In one embodiment, the system identifies n-grams (“snippets”) in a network flow's sequence-of-message-lengths that are strongly indicative of a given class of traffic and predicts a network flow's class by assessing the presence of snippets relevant to different classes.
    Type: Grant
    Filed: October 7, 2021
    Date of Patent: October 4, 2022
    Assignee: CORELIGHT, INC.
    Inventor: Julien Piet
  • Patent number: 11165675
    Abstract: A system and method for traffic classification using snippets and on-the-fly traffic classifiers can build traffic classifiers that leverage interpretable feature sets without the need to inspect payloads—ensuring functionality across clear-text and encrypted flows. In one embodiment, the system identifies n-grams (“snippets”) in a network flow's sequence-of-message-lengths that are strongly indicative of a given class of traffic and predicts a network flow's class by assessing the presence of snippets relevant to different classes.
    Type: Grant
    Filed: April 19, 2021
    Date of Patent: November 2, 2021
    Assignee: Corelight, Inc.
    Inventor: Julien Piet