公开(公告)号：US20220124487A1

公开(公告)日：2022-04-21

申请号：US17099796

申请日：2020-11-17

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Ting-Yu LIN ,  Ping-Chun CHEN ,  Chia-Min LAI

IPC: H04W12/00 ,  H04B1/16 ,  H04W12/10 ,  G06N3/08

Abstract: An RF fingerprint signal processing device configured for executing a machine learning algorithm on a plurality of input signals. The RF fingerprint signal processing device includes a receiver-feature determination circuit and a classifying determination circuit. The receiver-feature determination circuit is configured to compute on the plurality of input signals in a neural network. The classifying determination circuit is coupled with the receiver-feature determination circuit, and the classifying determination circuit is configured to send feedback information of a receiver-feature component to the receiver-feature determination circuit. The receiver-feature determination circuit decreases the receiver-feature weight of the neural network. The receiver-feature weight is associated with the receiver-feature component, and the receiver-feature weight which is decreased is applied for computing an output value of the neural network.

公开(公告)号：US20240129741A1

公开(公告)日：2024-04-18

申请号：US18056723

申请日：2022-11-18

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Yu Chi TUNG ,  Ping-Chun CHEN

IPC: H04W12/122 ,  H04L9/40 ,  H04W12/73

CPC classification number: H04W12/122 ,  H04L63/0236 ,  H04W12/73

Abstract: An information security early warning device is provided, which includes a data capturing circuit, a memory and a processor. The processor is used for running a virtual user equipment, a virtual base station and a virtual core network, and performing the following operations: when the first data flow is detected as non-malicious and abnormal, simulating transmission of the first data flow from the virtual base station to the virtual core network, and determining whether a connection can be established; when the connection can be established, updating a setting of the anomaly detection by using the first data flow; when the connection cannot be established, selecting an error log including a first malicious procedure code from multiple detection logs generated by the virtual core network; and updating the malicious feature database by using the first malicious procedure code and the first data flow.