Patents by Inventor Kui REN

Kui REN 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: 20220358417
    Abstract: Disclosed is a federated learning method for a k-means clustering algorithm. Horizontal federated learning includes the following steps: 1) initializing K clusters, and distributing, a local sample to a cluster closest to the sample; 2) calculating a new cluster center of the cluster; and 3) if the cluster center changes, then returning to step 1). Vertical federated learning includes the following steps: 1) running, the k-means clustering algorithm locally to obtain T local clusters and intersecting to obtain TL new clusters, or running an AP clustering algorithm to obtain Ti clusters and intersecting to obtain ?i=1LTi new clusters; 2) taking TL (?i=1LTi) new cluster centers as input samples, and initializing the K clusters; 3) distributing each sample to the cluster closest to the sample; 4) calculating a new cluster center of the cluster; and 5) if the cluster center changes, then returning to step 3).
    Type: Application
    Filed: July 8, 2022
    Publication date: November 10, 2022
    Inventors: Jian LIU, ZhiHua TIAN, Rui ZHANG, Xiaoyang HOU, Kui REN
  • Publication number: 20220358942
    Abstract: A method and an apparatus for acquiring semantic information, an electronic device and a storage medium are provided. The method includes: collecting an echo signal of vibrations of a throat; performing a Fourier transform on a waveform of each period of the echo signal to obtain a spectrogram of each period, wherein the spectrograms of M periods form a spectrogram set, the spectrogram set includes M spectrograms, and the spectrograms are arranged in sequence from first to last according to a return time sequence of the corresponding echo signal; extracting a characteristic waveform of the vibrations of the throat from the spectrogram set; segmenting the characteristic waveform to obtain characteristic segments containing the semantic information; and inputting the characteristic segments into a semantic acquisition model to acquire the semantic information.
    Type: Application
    Filed: August 9, 2021
    Publication date: November 10, 2022
    Inventors: Feng Lin, Chao Wang, Wenyao Xu, Kui Ren
  • Publication number: 20220351090
    Abstract: Disclosed is a federated learning method for decision tree-oriented horizontal. The method comprises the following steps: all participants searching for a quantile sketch of each feature in a data feature set based on dichotomy; the participants constructing a local histogram for each feature by using locally held data features according to the quantile sketch; adding noise satisfying differential privacy to all local histograms, and sending the local histograms to a coordinator after processing through the secure aggregation method; the coordinator merging the local histograms of each feature into a global histogram, and training a root node of a first decision tree according to the histogram; the coordinator sending information of the node to other participants; and all participants updating the local histograms and repeating the above process for training to obtain the trained decision trees.
    Type: Application
    Filed: July 8, 2022
    Publication date: November 3, 2022
    Inventors: ZhiHua TIAN, Rui ZHANG, Xiaoyang HOU, Jian LIU, Kui REN
  • Publication number: 20220188649
    Abstract: Provided is a decision tree-oriented vertical federated learning method, which mainly comprises the following steps: 1) all participants sorting local samples for each local feature, and then dividing the sorted samples into different blocks in sequence, each block being called a bucket; 2) for a group of samples corresponding to each feature, a bucket number of each sample under this feature having a certain probability to become other bucket numbers, and selecting an appropriate probability to make this encryption method meet the definition of differential privacy; 3) each participant sending serial numbers of buckets assigned to different samples under different features to the participant who holds a label, and this participant being called a coordinator;4) the coordinator training a decision tree model according to these samples, and no other participants being needed in the training process.
    Type: Application
    Filed: March 3, 2022
    Publication date: June 16, 2022
    Inventors: Jian LIU, Rui ZHANG, Zhihua TIAN, Xiaoyang HOU, Kui REN
  • Publication number: 20220101314
    Abstract: Disclosed is a coin-mixing service analysis method based on heuristic transaction analysis, including: selecting a target service to be analyzed; firstly, performing security analysis on the target service, and determining whether an API provided thereby contains vulnerability; if the API of the target service contains vulnerability, then obtaining sample transactions directly by means of the API containing the vulnerability; if the API of the target service contains no vulnerability, then obtaining sample transactions by using a small amount of Bitcoin for interaction with the service; using a heuristic transaction analysis method and determination standard to analyze the target service and the sample transaction thereof, and determine a service category to which the target service belongs; and for an obfuscated coin-mixing service, by means of a heuristic method, further using structural defects contained in transactions generated by the coin-mixing service to identify all coin-mixing transactions of the ob
    Type: Application
    Filed: December 14, 2021
    Publication date: March 31, 2022
    Inventors: Yajin ZHOU, Yufeng HU, Lei WU, Kui REN
  • Publication number: 20220083668
    Abstract: This invention discloses a method for discovering vulnerabilities of operating system access control based on model checking. In this method, security attribute and security specifications of operating system access control module are analyzed to construct the access control model. To discover vulnerabilities in the model, security analysis is performed for access control functionality with theorem proving techniques, and consistency of abstract machine specification and correctness and completeness of the components are verified with model checking tools. This method provides theoretical and technical support for studies in the field of operating system security.
    Type: Application
    Filed: July 27, 2021
    Publication date: March 17, 2022
    Inventors: Rui CHANG, Zhuoruo ZHANG, Shaoping PAN, Kui REN
  • Publication number: 20220014374
    Abstract: A physical token-based centralized authentication system for IoT devices is provided. The system transfers authentication of the IoT device on cloud to the IoT gateway for centralized authentication. User may respond on the IoT gateway via a U2F token to complete authentication of the IoT device. By transferring a kernel of authentication from a large number of scattered single IoT terminals to nodes of the trusted IoT gateway, the system overcomes defects such as numerous IoT devices, limited terminal resources, high authentication cost, and cumbersome operations while enhancing security of the IoT environment, thereby enhancing security of authentication for IoT environment and improving efficiencies of device authentication and management.
    Type: Application
    Filed: September 24, 2021
    Publication date: January 13, 2022
    Inventors: Feng LIN, Chao WANG, Hao LUO, Fan ZHANG, Jinsong HAN, Wenyao XU, Kui REN