Patents by Inventor Jialong Zhang

Jialong Zhang 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: 20190392305
    Abstract: Mechanisms are provided to implement an enhanced privacy deep learning system framework (hereafter “framework”). The framework receives, from a client computing device, an encrypted first subnet model of a neural network, where the first subnet model is one partition of multiple partitions of the neural network. The framework loads the encrypted first subnet model into a trusted execution environment (TEE) of the framework, decrypts the first subnet model, within the TEE, and executes the first subnet model within the TEE. The framework receives encrypted input data from the client computing device, loads the encrypted input data into the TEE, decrypts the input data, and processes the input data in the TEE using the first subnet model executing within the TEE.
    Type: Application
    Filed: June 25, 2018
    Publication date: December 26, 2019
    Inventors: Zhongshu Gu, Heqing Huang, Jialong Zhang, Dong Su, Dimitrios Pendarakis, Ian M. Molloy
  • Publication number: 20190370440
    Abstract: A framework to accurately and quickly verify the ownership of remotely-deployed deep learning models is provided without affecting model accuracy for normal input data. The approach involves generating a watermark, embedding the watermark in a local deep neural network (DNN) model by learning, namely, by training the local DNN model to learn the watermark and a predefined label associated therewith, and later performing a black-box verification against a remote service that is suspected of executing the DNN model without permission. The predefined label is distinct from a true label for a data item in training data for the model that does not include the watermark. Black-box verification includes simply issuing a query that includes a data item with the watermark, and then determining whether the query returns the predefined label.
    Type: Application
    Filed: June 4, 2018
    Publication date: December 5, 2019
    Applicant: International Business Machines Corporation
    Inventors: Zhongshu Gu, Heqing Huang, Marc Phillipe Stoecklin, Jialong Zhang
  • Publication number: 20190318099
    Abstract: Mechanisms are provided for evaluating a trained machine learning model to determine whether the machine learning model has a backdoor trigger. The mechanisms process a test dataset to generate output classifications for the test dataset, and generate, for the test dataset, gradient data indicating a degree of change of elements within the test dataset based on the output generated by processing the test dataset. The mechanisms analyze the gradient data to identify a pattern of elements within the test dataset indicative of a backdoor trigger. The mechanisms generate, in response to the analysis identifying the pattern of elements indicative of a backdoor trigger, an output indicating the existence of the backdoor trigger in the trained machine learning model.
    Type: Application
    Filed: April 16, 2018
    Publication date: October 17, 2019
    Inventors: Wilka Carvalho, Bryant Chen, Benjamin J. Edwards, Taesung Lee, Ian M. Molloy, Jialong Zhang
  • Publication number: 20190306719
    Abstract: Advanced persistent threats to a mobile device are detected and prevented by leveraging the built-in mandatory access control (MAC) environment in the mobile operating system in a “stateful” manner. To this end, the MAC mechanism is placed in a permissive mode of operation wherein permission denials are logged but not enforced. The mobile device security environment is augmented to include a monitoring application that is instantiated with system privileges. The application monitors application execution parameters of one or more mobile applications executing on the device. These application execution parameters including, without limitation, the permission denials, are collected and used by the monitoring application to facilitate a stateful monitoring of the operating system security environment. By assembling security-sensitive events over a time period, the system identifies an advanced persistent threat (APT) that otherwise leverages multiple steps using benign components.
    Type: Application
    Filed: March 28, 2018
    Publication date: October 3, 2019
    Applicant: International Business Machines Corporation
    Inventors: Suresh Chari, Zhongshu Gu, Heqing Huang, Xiaokui Shu, Jialong Zhang
  • Publication number: 20190108339
    Abstract: Approaches to deactivating evasive malware. In an approach, a computer system installs an imitating resource in the computer system and the imitating resource creates an imitating environment of malware analysis, wherein the imitating resource causes the evasive malware to respond to the imitating environment of the malware analysis as to a real environment of the malware analysis. In the imitating environment of malware analysis, the evasive malware determines not to perform malicious behavior. In another approach, a computer system intercepts a call from the evasive malware to a resource on the computer system and returns a virtual resource to the call, wherein in the virtual resource one or more values of the resource on the computer system are modified.
    Type: Application
    Filed: October 6, 2017
    Publication date: April 11, 2019
    Inventors: ZHONGSHU GU, HEQING HUANG, JIYONG JANG, DHILUNG HANG KIRAT, XIAOKUI SHU, MARC P. STOECKLIN, JIALONG ZHANG
  • Patent number: 9578042
    Abstract: Identifying malicious servers is provided. Malicious edges between server vertices corresponding to visible servers and invisible servers involved in network traffic redirection chains are determined based on determined graph-based features within a bipartite graph corresponding to invisible server vertices involved in the network traffic redirection chains and determined distance-based features corresponding to the invisible server vertices involved in the network traffic redirection chains. Malicious server vertices are identified in the bipartite graph based on the determined malicious edges between the server vertices corresponding to the visible servers and invisible servers involved in the network traffic redirection chains. Access by client devices is blocked to malicious servers corresponding to the identified malicious server vertices in the bipartite graph.
    Type: Grant
    Filed: June 18, 2015
    Date of Patent: February 21, 2017
    Assignee: International Business Machines Corporation
    Inventors: Xin Hu, Jiyong Jang, Ting Wang, Jialong Zhang
  • Patent number: 9571518
    Abstract: Identifying malicious servers is provided. Malicious edges between server vertices corresponding to visible servers and invisible servers involved in network traffic redirection chains are determined based on determined graph-based features within a bipartite graph corresponding to invisible server vertices involved in the network traffic redirection chains and determined distance-based features corresponding to the invisible server vertices involved in the network traffic redirection chains. Malicious server vertices are identified in the bipartite graph based on the determined malicious edges between the server vertices corresponding to the visible servers and invisible servers involved in the network traffic redirection chains. Access by client devices is blocked to malicious servers corresponding to the identified malicious server vertices in the bipartite graph.
    Type: Grant
    Filed: March 6, 2015
    Date of Patent: February 14, 2017
    Assignee: International Business Machines Corporation
    Inventors: Xin Hu, Jiyong Jang, Ting Wang, Jialong Zhang
  • Publication number: 20160261608
    Abstract: Identifying malicious servers is provided. Malicious edges between server vertices corresponding to visible servers and invisible servers involved in network traffic redirection chains are determined based on determined graph-based features within a bipartite graph corresponding to invisible server vertices involved in the network traffic redirection chains and determined distance-based features corresponding to the invisible server vertices involved in the network traffic redirection chains. Malicious server vertices are identified in the bipartite graph based on the determined malicious edges between the server vertices corresponding to the visible servers and invisible servers involved in the network traffic redirection chains. Access by client devices is blocked to malicious servers corresponding to the identified malicious server vertices in the bipartite graph.
    Type: Application
    Filed: June 18, 2015
    Publication date: September 8, 2016
    Inventors: Xin Hu, Jiyong Jang, Ting Wang, Jialong Zhang
  • Publication number: 20160261626
    Abstract: Identifying malicious servers is provided. Malicious edges between server vertices corresponding to visible servers and invisible servers involved in network traffic redirection chains are determined based on determined graph-based features within a bipartite graph corresponding to invisible server vertices involved in the network traffic redirection chains and determined distance-based features corresponding to the invisible server vertices involved in the network traffic redirection chains. Malicious server vertices are identified in the bipartite graph based on the determined malicious edges between the server vertices corresponding to the visible servers and invisible servers involved in the network traffic redirection chains. Access by client devices is blocked to malicious servers corresponding to the identified malicious server vertices in the bipartite graph.
    Type: Application
    Filed: March 6, 2015
    Publication date: September 8, 2016
    Inventors: Xin Hu, Jiyong Jang, Ting Wang, Jialong Zhang
  • Patent number: 9088598
    Abstract: A method for detecting malicious servers. The method includes analyzing network traffic data to generate a main similarity measure and a secondary similarity measure for each server pair found in the network traffic data, extracting a main subset and a secondary subset of servers based on the main similarity measure and the secondary similarity measure, identifying a server that belongs to the main subset and the secondary subset, and determining a suspicious score of the server based on at least a first similarity density measure of the main subset, a second similarity density measure of the secondary subset, and a commonality measure of the main subset and the secondary subset.
    Type: Grant
    Filed: November 14, 2013
    Date of Patent: July 21, 2015
    Assignee: Narus, Inc.
    Inventors: Jialong Zhang, Sabyasachi Saha, Guofei Gu, Sung-Ju Lee, Bruno Nardelli