Access point identification method and system using machine learning

摘要

The present invention is an AP identification method and system using machine learning for identifying a normal AP, an unauthorized AP, and a rogue AP by extracting a feature value from a beacon frame packet of an AP (Access point) using machine learning. It is about. In the AP identification method using machine learning according to an embodiment of the present invention, a beacon frame of a neighboring AP is collected in a pcapng file format (S10), and the collected pcapng file is converted into a CSV file for processing. It may include a step S20 and a step S30 of extracting a feature value for identifying an AP in a wireless communication environment using the converted CSV file. In addition, the feature values calculated and extracted in step (S40) using a machine learning classification algorithm and calculating and extracting feature values from the beacon frames of the previously stored AP based on feature values for identifying the extracted AP. Learning (S50) and determining whether the identifier extracted from the beacon frame of the AP to be identified has been learned before (S60) and when the determination result of the (S60) step has previously learned It may include determining a normal AP and a rogue AP by using the extracted feature value (S70).