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).

  • Patent number: 12045713
    Abstract: A method, apparatus and computer program product to protect a deep neural network (DNN) having a plurality of layers including one or more intermediate layers. In this approach, a training data set is received. During training of the DNN using the received training data set, a representation of activations associated with an intermediate layer is recorded. For at least one or more of the representations, a separate classifier (model) is trained. The classifiers, collectively, are used to train an outlier detection model. Following training, the outliner detection model is used to detect an adversarial input on the deep neural network. The outlier detection model generates a prediction, and an indicator whether a given input is the adversarial input. According to a further aspect, an action is taken to protect a deployed system associated with the DNN in response to detection of the adversary input.
    Type: Grant
    Filed: November 17, 2020
    Date of Patent: July 23, 2024
    Assignee: International Business Machines Corporation
    Inventors: Jialong Zhang, Zhongshu Gu, Jiyong Jang, Marc Philippe Stoecklin, Ian Michael Molloy
  • Patent number: 11886989
    Abstract: Using a deep learning inference system, respective similarities are measured for each of a set of intermediate representations to input information used as an input to the deep learning inference system. The deep learning inference system includes multiple layers, each layer producing one or more associated intermediate representations. Selection is made of a subset of the set of intermediate representations that are most similar to the input information. Using the selected subset of intermediate representations, a partitioning point is determined in the multiple layers used to partition the multiple layers into two partitions defined so that information leakage for the two partitions will meet a privacy parameter when a first of the two partitions is prevented from leaking information. The partitioning point is output for use in partitioning the multiple layers of the deep learning inference system into the two partitions.
    Type: Grant
    Filed: September 10, 2018
    Date of Patent: January 30, 2024
    Assignee: International Business Machines Corporation
    Inventors: Zhongshu Gu, Heqing Huang, Jialong Zhang, Dong Su, Dimitrios Pendarakis, Ian Michael Molloy
  • Patent number: 11828781
    Abstract: This application provides a transmission absorbing structure and an antenna in-band characteristics test system, relating to design of microwave antennas for radar and communication systems. The transmission absorbing structure includes a coupling feed structure provided with coupling slots for energy coupling with a to-be-tested antenna, two equivalent electric wall structures parallel to each other, and two equivalent magnetic wall structures parallel to each other. The two equivalent electric wall structures and the two equivalent magnetic wall structures together enclose the coupling feed structure, and form a transverse electromagnetic mode (TEM) waveguide. The system includes a vector network analyzer, a to-be-tested antenna electrically connected to the vector network analyzer, and a transmission absorbing structure.
    Type: Grant
    Filed: June 8, 2023
    Date of Patent: November 28, 2023
    Assignee: 38TH RESEARCH INSTITUTE, CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION
    Inventors: Xiaopeng Lu, Yan Li, Lei Sheng, Zicheng Zhou, Yufan Yao, Jialong Zhang
  • Patent number: 11829879
    Abstract: Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.
    Type: Grant
    Filed: September 23, 2022
    Date of Patent: November 28, 2023
    Assignee: International Business Machines Corporation
    Inventors: Jialong Zhang, Frederico Araujo, Teryl Taylor, Marc Philippe Stoecklin
  • Patent number: 11816575
    Abstract: Deep learning training service framework mechanisms are provided. The mechanisms receive encrypted training datasets for training a deep learning model, execute a FrontNet subnet model of the deep learning model in a trusted execution environment, and execute a BackNet subnet model of the deep learning model external to the trusted execution environment. The mechanisms decrypt, within the trusted execution environment, the encrypted training datasets and train the FrontNet subnet model and BackNet subnet model of the deep learning model based on the decrypted training datasets. The FrontNet subnet model is trained within the trusted execution environment and provides intermediate representations to the BackNet subnet model which is trained external to the trusted execution environment using the intermediate representations. The mechanisms release a trained deep learning model comprising a trained FrontNet subnet model and a trained BackNet subnet model, to the one or more client computing devices.
    Type: Grant
    Filed: September 7, 2018
    Date of Patent: November 14, 2023
    Inventors: Zhongshu Gu, Heqing Huang, Jialong Zhang, Dong Su, Dimitrios Pendarakis, Ian M. Molloy
  • Publication number: 20230324444
    Abstract: This application provides a transmission absorbing structure and an antenna in-band characteristics test system, relating to design of microwave antennas for radar and communication systems. The transmission absorbing structure includes a coupling feed structure provided with coupling slots for energy coupling with a to-be-tested antenna, two equivalent electric wall structures parallel to each other, and two equivalent magnetic wall structures parallel to each other. The two equivalent electric wall structures and the two equivalent magnetic wall structures together enclose the coupling feed structure, and form a transverse electromagnetic mode (TEM) waveguide. The system includes a vector network analyzer, a to-be-tested antenna electrically connected to the vector network analyzer, and a transmission absorbing structure.
    Type: Application
    Filed: June 8, 2023
    Publication date: October 12, 2023
    Inventors: Xiaopeng LU, Yan LI, Lei SHENG, Zicheng ZHOU, Yufan YAO, Jialong ZHANG
  • Patent number: 11775637
    Abstract: Mechanisms are provided for detecting abnormal system call sequences in a monitored computing environment. The mechanisms receive, from a computing system resource of the monitored computing environment, a system call of an observed system call sequence for evaluation. A trained recurrent neural network (RNN), trained to predict system call sequences, processes the system call to generate a prediction of a subsequent system call in a predicted system call sequence. Abnormal call sequence logic compares the subsequent system call in the predicted system call sequence to an observed system call in the observed system call sequence and identifies a difference between the predicted system call sequence and the observed system call sequence based on results of the comparing. The abnormal call sequence logic generates an alert notification in response to identifying the difference.
    Type: Grant
    Filed: March 14, 2022
    Date of Patent: October 3, 2023
    Assignee: International Business Machines Corporation
    Inventors: Heqing Huang, Taesung Lee, Ian M. Molloy, Zhongshu Gu, Jialong Zhang, Josyula R. Rao
  • Patent number: 11632393
    Abstract: Malware is detected and mitigated by differentiating HTTP error generation patterns between errors generated by malware, and errors generated by benign users/software. In one embodiment, a malware detector system receives traffic that includes HTTP errors and successful HTTP requests. Error traffic and the successful request traffic are segmented for further analysis. The error traffic is supplied to a clustering component, which groups the errors, e.g., based on their URI pages and parameters. During clustering, various statistical features are extracted (as feature vectors) from one or more perspectives, namely, error provenance, error generation, and error recovery. The feature vectors are supplied to a classifier component, which is trained to distinguish malware-generated errors from benign errors. Once trained, the classifier takes an error cluster and its surrounding successful HTTP requests as inputs, and it produces a verdict on whether a particular cluster is malicious.
    Type: Grant
    Filed: October 16, 2020
    Date of Patent: April 18, 2023
    Assignee: International Business Machines Corporation
    Inventors: Jialong Zhang, Jiyong Jang, Marc Philippe Stoecklin
  • Publication number: 20230019198
    Abstract: Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.
    Type: Application
    Filed: September 23, 2022
    Publication date: January 19, 2023
    Inventors: Jialong Zhang, Frederico Araujo, Teryl Taylor, Marc Philippe Stoecklin
  • Patent number: 11501156
    Abstract: Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.
    Type: Grant
    Filed: June 28, 2018
    Date of Patent: November 15, 2022
    Assignee: International Business Machines Corporation
    Inventors: Jialong Zhang, Frederico Araujo, Teryl Taylor, Marc Philippe Stoecklin
  • Patent number: 11443182
    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: Grant
    Filed: June 25, 2018
    Date of Patent: September 13, 2022
    Assignee: International Business Machines Corporation
    Inventors: Zhongshu Gu, Heqing Huang, Jialong Zhang, Dong Su, Dimitrios Pendarakis, Ian M. Molloy
  • Publication number: 20220269942
    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: May 13, 2022
    Publication date: August 25, 2022
    Inventors: Zhongshu Gu, Heqing Huang, Jialong Zhang, Dong Su, Dimitrios Pendarakis, Ian M. Molloy
  • Publication number: 20220207137
    Abstract: Mechanisms are provided for detecting abnormal system call sequences in a monitored computing environment. The mechanisms receive, from a computing system resource of the monitored computing environment, a system call of an observed system call sequence for evaluation. A trained recurrent neural network (RNN), trained to predict system call sequences, processes the system call to generate a prediction of a subsequent system call in a predicted system call sequence. Abnormal call sequence logic compares the subsequent system call in the predicted system call sequence to an observed system call in the observed system call sequence and identifies a difference between the predicted system call sequence and the observed system call sequence based on results of the comparing. The abnormal call sequence logic generates an alert notification in response to identifying the difference.
    Type: Application
    Filed: March 14, 2022
    Publication date: June 30, 2022
    Inventors: Heqing Huang, Taesung Lee, Ian M. Molloy, Zhongshu Gu, Jialong Zhang, Josyula R. Rao
  • Publication number: 20220156563
    Abstract: A method, apparatus and computer program product to protect a deep neural network (DNN) having a plurality of layers including one or more intermediate layers. In this approach, a training data set is received. During training of the DNN using the received training data set, a representation of activations associated with an intermediate layer is recorded. For at least one or more of the representations, a separate classifier (model) is trained. The classifiers, collectively, are used to train an outlier detection model. Following training, the outliner detection model is used to detect an adversarial input on the deep neural network. The outlier detection model generates a prediction, and an indicator whether a given input is the adversarial input. According to a further aspect, an action is taken to protect a deployed system associated with the DNN in response to detection of the adversary input.
    Type: Application
    Filed: November 17, 2020
    Publication date: May 19, 2022
    Applicant: International Business Machines Corporation
    Inventors: Jialong Zhang, Zhongshu Gu, Jiyong Jang, Marc Philippe Stoecklin, Ian Michael Molloy
  • Publication number: 20220124102
    Abstract: Malware is detected and mitigated by differentiating HTTP error generation patterns between errors generated by malware, and errors generated by benign users/software. In one embodiment, a malware detector system receives traffic that includes HTTP errors and successful HTTP requests. Error traffic and the successful request traffic are segmented for further analysis. The error traffic is supplied to a clustering component, which groups the errors, e.g., based on their URI pages and parameters. During clustering, various statistical features are extracted (as feature vectors) from one or more perspectives, namely, error provenance, error generation, and error recovery. The feature vectors are supplied to a classifier component, which is trained to distinguish malware-generated errors from benign errors. Once trained, the classifier takes an error cluster and its surrounding successful HTTP requests as inputs, and it produces a verdict on whether a particular cluster is malicious.
    Type: Application
    Filed: October 16, 2020
    Publication date: April 21, 2022
    Applicant: International Business Machines Corporation
    Inventors: Jialong Zhang, Jiyong Jang, Marc Philippe Stoecklin
  • Patent number: 11310232
    Abstract: There are provided a network identity authentication method, a network identity authentication system, a user agent device used in the network identity authentication method and the network identity authentication system, and a computer-readable storage medium. The network identity authentication method includes: acquiring, by a user agent, identity information and a registration rule of a target website via a network terminal; acquiring registration information for the target website based on the identity information or generating registration information for the target website according to the registration rule; transmitting the identity information and the registration information to a server agent and sending, by the server agent based on the identity information and the registration information, an authentication request to a website server to complete an authentication process.
    Type: Grant
    Filed: September 25, 2018
    Date of Patent: April 19, 2022
    Assignee: GUANGDONG UNIVERSITY OF TECHNOLOGY
    Inventors: Wenyin Liu, Xin Li, Zhiheng Shen, Jialong Zhang, Shuai Fan, Qixiang Zhang, Jiahong Wu
  • Patent number: 11301563
    Abstract: Mechanisms are provided for detecting abnormal system call sequences in a monitored computing environment. The mechanisms receive, from a computing system resource of the monitored computing environment, a system call of an observed system call sequence for evaluation. A trained recurrent neural network (RNN), trained to predict system call sequences, processes the system call to generate a prediction of a subsequent system call in a predicted system call sequence. Abnormal call sequence logic compares the subsequent system call in the predicted system call sequence to an observed system call in the observed system call sequence and identifies a difference between the predicted system call sequence and the observed system call sequence based on results of the comparing. The abnormal call sequence logic generates an alert notification in response to identifying the difference.
    Type: Grant
    Filed: March 13, 2019
    Date of Patent: April 12, 2022
    Assignee: International Business Machines Corporation
    Inventors: Heqing Huang, Taesung Lee, Ian M. Molloy, Zhongshu Gu, Jialong Zhang, Josyula R. Rao
  • Patent number: 11188789
    Abstract: One embodiment provides a method comprising receiving a training set comprising a plurality of data points, where a neural network is trained as a classifier based on the training set. The method further comprises, for each data point of the training set, classifying the data point with one of a plurality of classification labels using the trained neural network, and recording neuronal activations of a portion of the trained neural network in response to the data point. The method further comprises, for each classification label that a portion of the training set has been classified with, clustering a portion of all recorded neuronal activations that are in response to the portion of the training set, and detecting one or more poisonous data points in the portion of the training set based on the clustering.
    Type: Grant
    Filed: August 7, 2018
    Date of Patent: November 30, 2021
    Assignee: International Business Machines Corporation
    Inventors: Bryant Chen, Wilka Carvalho, Heiko H. Ludwig, Ian Michael Molloy, Taesung Lee, Jialong Zhang, Benjamin J. Edwards
  • Patent number: 11184374
    Abstract: An automated method for cyberattack detection and prevention in an endpoint. The technique monitors and protects the endpoint by recording inter-process events, creating an inter-process activity graph based on the recorded inter-process events, matching the inter-process activity (as represented in the activity graph) against known malicious or suspicious behavior (as embodied in a set of one or more pattern graphs), and performing a post-detection operation in response to a match between an inter-process activity and a known malicious or suspicious behavior pattern. Preferably, matching involves matching a subgraph in the activity graph with a known malicious or suspicious behavior pattern as represented in the pattern graph. During this processing, preferably both direct and indirect inter-process activities at the endpoint (or across a set of endpoints) are compared to the known behavior patterns.
    Type: Grant
    Filed: October 12, 2018
    Date of Patent: November 23, 2021
    Assignee: International Business Machines Corporation
    Inventors: Xiaokui Shu, Zhongshu Gu, Heqing Huang, Marc Philippe Stoecklin, Jialong Zhang
  • Patent number: 11163860
    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: Grant
    Filed: June 4, 2018
    Date of Patent: November 2, 2021
    Assignee: International Business Machines Corporation
    Inventors: Zhongshu Gu, Heqing Huang, Marc Phillipe Stoecklin, Jialong Zhang