A novel botnet attack detection for IoT networks based on communication graphs  

作　　者：David Concejal Munoz Antonio del-Corte Valiente 

机构地区：[1]Inetum Espana S.A.,C/Maria de Portugal,9-11,Building 1,28050 Madrid,Spain [2]Department of Computer Engineering,Polytechnic School,University of Alcala,Madrid-Barcelona Road Km 33.6.Alcala de Henares,28871 Madrid,Spain

出　　处：《Cybersecurity》2024年第4期19-35,共17页网络空间安全科学与技术（英文）

摘　　要：Intrusion detection systems have been proposed for the detection of botnet attacks.Various types of centralized or distributed cloud-based machine learning and deep learning models have been suggested.However,the emergence of the Internet of Things(loT)has brought about a huge increase in connected devices,necessitating a different approach.In this paper,we propose to perform detection on IoT-edge devices.The suggested architecture includes an anomaly intrusion detection system in the application layer of IoT-edge devices,arranged in software-defined networks.loT-edge devices request information from the software-defined networks controller about their own behaviour in the network.This behaviour is represented by communication graphs and is novel for IoT networks.This representation better characterizes the behaviour of the device than the traditional analysis of network traffc,with a lower volume of information.Botnet attack scenarios are simulated with the IoT-23 dataset.Experimental results show that attacks are detected with high accuracy using a deep learning model with low device memory requirements and significant storage reduction for training.

关 键 词：Autoencoders Communication graphs Cyberattacks Internet of Things 

分 类 号：TN915.08[电子电信—通信与信息系统]