IoTDevID: A Behavior-Based Device Identification Method for the IoT

Abstract

While the use of the Internet of Things is becoming more and more popular, many security vulnerabilities are emerging with the large number of devices being introduced to the market. In this environment, IoT device identification methods provide a preventive security measure as an important factor in identifying these devices and detecting the vulnerabilities they suffer from. In this study, we present a method that identifies devices in the Aalto dataset using the convolutional neural network (CNN).

Intelligent device identification based on traffic time-series features

“…One MAC address corresponds to multiple device labels. This may be due to devices that use low-power protocols usually not having their own IP or MAC address and instead use the IP or MAC address of the gateway [7]. In a real environment, it is difficult to distinguish whether the data comes from the gateway or the smart device connected to the gateway, so it is not necessary to deliberately distinguish the collected data as coming from the gateway or from a connected smart device.…”

“…This article uses the scapy tool to parse data packets and extract protocol features. This paper directly used the 96 protocol features provided by [7], such as port number, protocol type, packet size, and numerous protocol identifiers. In addition, two features of payload and entropy were also included to provide information about the effective payload features.…”

“…Unlike Ref. [7], we added timestamp information for each packet to facilitate grouping of packets based on time series features in the subsequent analysis.…”

Identifying key sectors based on cascading effect along paths in the embodied CO2 emission flow network in Beijing-Tianjin-Hebei region, China

“…Moving into the year 2020, researchers [70,108,109] not only continued to optimize algorithms but also introduced more representative features that were better suited for CIoT scenarios. Considering the computing cost brought by a large number of features, works published in 2021 to 2022 [80,110,111] focus on feature reduction algorithms to acquire key features that enhance classification accuracy and efficiency. Moreover, they also considered greater device diversity and larger datasets [69,111,112].…”

“…Considering the computing cost brought by a large number of features, works published in 2021 to 2022 [80,110,111] focus on feature reduction algorithms to acquire key features that enhance classification accuracy and efficiency. Moreover, they also considered greater device diversity and larger datasets [69,111,112].…”