ALEXANDRIA, Va., Sept. 8 -- United States Patent no. 12,731,382, issued on Sept. 8, was assigned to BEIHANG UNIVERSITY (Beijing) and BEIJING UNIVERSITY OF TECHNOLOGY (Beijing).
"Deep learning backdoor attack method and device based on ordinal network and medium" was invented by Yunfeng Lu (Beijing), Chao Li (Beijing), Yanfang Liu (Beijing), Guoyan Chen (Beijing), Zhiming Gui (Beijing) and Xinrui Ma (Beijing).
According to the abstract* released by the U.S. Patent & Trademark Office: "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...