Patents by Inventor ZHIMING GUI

ZHIMING GUI 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: 12731382
    Abstract: The present invention discloses a deep learning backdoor attack method and device based on an ordinal network and a medium, which belongs to the technical field of neural network security. The method comprises: obtaining a training sample image; generating an ordinal network based on the training sample image, wherein the ordinal network is used for representing an exact structure of an image; and generating a trigger by using the ordinal network. Through the above method, and the device and the medium for realizing the above method, the present invention uses the ordinal network to generate the trigger, improves the concealability of a poisoning sample compared with poisoning samples generated by other attack methods, and can promote the further research of a hidden backdoor attack defense method in the academic circle.
    Type: Grant
    Filed: March 26, 2024
    Date of Patent: September 8, 2026
    Assignees: BEIHANG UNIVERSITY, BEIJING UNIVERSITY OF TECHNOLOGY
    Inventors: Yunfeng Lu, Chao Li, Yanfang Liu, Guoyan Chen, Zhiming Gui, Xinrui Ma
  • Publication number: 20250308213
    Abstract: The present invention discloses a deep learning backdoor attack method and device based on an ordinal network and a medium, which belongs to the technical field of neural network security. The method comprises: obtaining a training sample image; generating an ordinal network based on the training sample image, wherein the ordinal network is used for representing an exact structure of an image; and generating a trigger by using the ordinal network. Through the above method, and the device and the medium for realizing the above method, the present invention uses the ordinal network to generate the trigger, improves the concealability of a poisoning sample compared with poisoning samples generated by other attack methods, and can promote the further research of a hidden backdoor attack defense method in the academic circle.
    Type: Application
    Filed: March 26, 2024
    Publication date: October 2, 2025
    Inventors: YUNFENG LU, CHAO LI, YANFANG LIU, GUOYAN CHEN, ZHIMING GUI, XINRUI MA