关键词: 入侵检测系统, 深度学习, 序列模型, 物联网安全, 无线传感网安全

Abstract: With the rapid development of the Internet of Things, more and more IoT node devices are deployed, but the accompanying security issues cannot be ignored. The network layer node devices of the Internet of Things mainly communicate through the wireless sensor network, which is more open and more vulnerable to network attacks such as denial of service than the Internet. Aiming at the security problems faced by wireless sensor networks, an intrusion detection system based on sequence model is proposed to detect and alarm network intrusion, which achieves a good recognition rate and a low false positive rate. In addition, based on the host-side security problem faced by IoT-aware node devices, an intrusion detection system based on simple sequence model is proposed based on the node overhead problem. The experimental results show that the two intrusion detection systems for the Internet of Things network layer and the sensing layer have achieved good accuracy and can effectively protect the security of the Internet of Things.

Key words: Intrusion Detection System (IDS), deep learning, sequence model, Internet of Things security, Wireless sensor network security