Patents by Inventor Farhan Tejani

Farhan Tejani 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).

  • Protecting cognitive systems from gradient based attacks through the use of deceiving gradients
    Patent number: 10657259
    Abstract: Mechanisms are provided for providing a hardened neural network. The mechanisms configure the hardened neural network executing in the data processing system to introduce noise in internal feature representations of the hardened neural network. The noise introduced in the internal feature representations diverts gradient computations associated with a loss surface of the hardened neural network. The mechanisms configure the hardened neural network executing in the data processing system to implement a merge layer of nodes that combine outputs of adversarially trained output nodes of the hardened neural network with output nodes of the hardened neural network trained based on the introduced noise. The mechanisms process, by the hardened neural network, input data to generate classification labels for the input data and thereby generate augmented input data which is output to a computing system for processing to perform a computing operation.
    Type: Grant
    Filed: November 1, 2017
    Date of Patent: May 19, 2020
    Assignee: International Business Machines Corporation
    Inventors: Taesung Lee, Ian M. Molloy, Farhan Tejani
  • Protecting Cognitive Systems from Gradient Based Attacks through the Use of Deceiving Gradients
    Publication number: 20190130110
    Abstract: Mechanisms are provided for providing a hardened neural network. The mechanisms configure the hardened neural network executing in the data processing system to introduce noise in internal feature representations of the hardened neural network. The noise introduced in the internal feature representations diverts gradient computations associated with a loss surface of the hardened neural network. The mechanisms configure the hardened neural network executing in the data processing system to implement a merge layer of nodes that combine outputs of adversarially trained output nodes of the hardened neural network with output nodes of the hardened neural network trained based on the introduced noise. The mechanisms process, by the hardened neural network, input data to generate classification labels for the input data and thereby generate augmented input data which is output to a computing system for processing to perform a computing operation.
    Type: Application
    Filed: November 1, 2017
    Publication date: May 2, 2019
    Inventors: Taesung Lee, Ian M. Molloy, Farhan Tejani