面向物联网的僵尸网络流量检测与应用

Botnet Traffic Detection and Application for the Internet of Things

物联网设备比个人主机更加容易遭受攻击,物联网设备的激增导致基于物联网的僵尸网络攻击的增加。为了减轻来自物联网设备僵尸网络的威胁,需要提高面向物联网的基于流量的僵尸网络流量检测效率和精度。实验出轻量级检测模型方法,应用到自适应的迁移学习策略中去,解决异构物联网中僵尸网络流量的概念漂移问题,进行恶意流量检测。经过Mirai和Gafgyt僵尸网络流量公开数据集的测试,证明检测方法能够精准的二分类识别僵尸网络流量。

IoT devices are more vulnerable to attacks than personal hosts. The proliferation of IoT devices has led to an increase in botnet attacks based on the IoT. In order to mitigate the threat from the botnet of IoT devices, it is necessary to improve the efficiency and accuracy of traffic detection of the traffic based botnet for IoT. The lightweight detection model method is tested and applied to the adaptive migration learning strategy to solve the concept drift problem of botnet traffic in the heterogeneous Internet of Things and detect malicious traffic. The test of Mirai and Gafgyt botnet traffic open data sets proves that the detection method can accurately identify botnet traffic by two classifications.