摘要
随着物联网(IoT)的快速发展,连接到网络的设备数量急剧增加。设备识别已成为防止恶意攻击和确保网络安全的关键。文章提出了一种基于到达时间(IAT)的设备指纹识别机制,利用IAT生成设备指纹并验证物联网设备,使用网络嗅探器捕获网络流量,提取数据包字段并计算IAT值。通过收集网络数据,建立了基于IAT的数据集,利用监督机器学习算法来识别设备。最后,在模拟和真实环境中评估了提出的设备指纹算法。结果表明,该方法在仿真中的准确率在95%以上,在实际网络中的准确率高达99%。
Given the rapid development of the Internet of Things(IoT), the number of devices connected to the network has increased dramatically. Consequently, device identification has become a crucial aspect of preventing malicious attacks and ensuring network security. In this paper, we present a novel device fingerprinting mechanism based on inter arrival time(IAT) to identify devices. We utilize IAT, the passive method, to generate device fingerprints and verify IoT devices. In the proposed mechanism, the network sniffer is used to capture network traffic from which we extract packet fields and calculate IAT values. By collecting the network records, we build the IATbased data set and utilize supervised machine learning algorithms to identify devices. Finally, we evaluate our proposed device fingerprinting in both simulated and real-world environments. The results show that our method achieves accuracy above 95% in the simulation and up to 99% in a real-world network.
作者
宫婷
林智君
阮天翔
Gong Ting;Lin Zhijun;Ruan Tianxiang(Aeronautics Computing Technology Research Institute,Xi’an 710068,China;Northwestern Polytechnical University,Xi’an 710072,China)
出处
《无线互联科技》
2022年第22期4-7,共4页
Wireless Internet Technology
