Patents by Inventor Roman Levenstein

Roman Levenstein 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 protecting neural network weights
    Patent number: 11487888
    Abstract: The disclosed computer-implemented method may include (i) identifying a neural network that comprises an interconnected set of nodes organized in a set of layers represented by a plurality of matrices that each comprise a plurality of weights, where each weight represents a connection between a node in the interconnected set of nodes that resides in one layer in the set of layers and an additional node in the set of interconnected nodes that resides in a different layer in the set of layers, (ii) encrypting, using an encryption cipher, the plurality of weights, (iii) detecting that execution of the neural network has been initiated, and (iv) decrypting, using the encryption cipher, the plurality of weights in response to detecting that the execution of the neural network has been initiated. Various other methods, systems, and computer-readable media are also disclosed.
    Type: Grant
    Filed: June 1, 2020
    Date of Patent: November 1, 2022
    Assignee: Meta Platforms, Inc.
    Inventors: Nadav Rotem, Abdulkadir Utku Diril, Mikhail Smelyanskiy, Jong Soo Park, Roman Levenstein
  • Systems and methods for protecting neural network weights
    Patent number: 10719613
    Abstract: The disclosed computer-implemented method may include (i) identifying a neural network that comprises an interconnected set of nodes organized in a set of layers represented by a plurality of matrices that each comprise a plurality of weights, where each weight represents a connection between a node in the interconnected set of nodes that resides in one layer in the set of layers and an additional node in the set of interconnected nodes that resides in a different layer in the set of layers, (ii) encrypting, using an encryption cipher, the plurality of weights, (iii) detecting that execution of the neural network has been initiated, and (iv) decrypting, using the encryption cipher, the plurality of weights in response to detecting that the execution of the neural network has been initiated. Various other methods, systems, and computer-readable media are also disclosed.
    Type: Grant
    Filed: February 23, 2018
    Date of Patent: July 21, 2020
    Assignee: Facebook, Inc.
    Inventors: Nadav Rotem, Abdulkadir Utku Diril, Mikhail Smelyanskiy, Jong Soo Park, Roman Levenstein