| Popis: |
Recently, security issues have become more serious with the spread of IoT devices. To reduce the security risks when using communication devices, network administrators should know detailed information of all devices connected in the network and control them accordingly. Although there are many studies about identifying devices based on information from the network, there is a limit to improving the accuracy of device identification by using a single identification method.In this paper, we propose a new method to improve the accuracy of device identification by using a combination of results from multiple identification methods. We define a new index, called similarity, between multiple devices by using the results from multiple identification methods and identify devices based on the similarity. The results of evaluations for communication devices connected to a real network show that our method can improve the accuracy of device identification by 23.0 percent. |
