基于深度学习的物联网入侵检测研究

Research on IoT Intrusion Detection Based on Deep Learning

针对传统物联网入侵检测准确率低、速度慢、适应性差等缺点,提出一种基于深度学习的物联网入侵检测方法。对物联网入侵检测数据集进行预处理操作,使用主成分分析方法对数据集进行降维处理,提取到关键数据集关键特征;将其输入到深度学习网络之中,输出得到攻击类型输出;最后,通过参数调优得到最佳物联网入侵检测分类器,并进行仿真实验。结果表明,深度学习网络能提高物联网攻击数据检测精度和运行效率,提升物联网安全性。

Aiming at the disadvantages of low accuracy,slow speed and poor adaptability of traditional IoT intrusion detection,an IoT intrusion detection method based on deep learning is proposed.Firstly,the data set of IoT intrusion detection is preprocessed,and the dimension reduction process is carried out by using principal component analysis method to extract the key features of the key data set.Then it is input into the deep learning network to get the attack type output.Finally,the optimal IoT intrusion detection classifier is obtained by parameter tuning,and simulation experiments are carried out.Experimental results show that deep learning network can improve the detection accuracy and operation efficiency of IoT attack data,and improve the security of IoT.