DDoS Attack Detection on Botnet Devices
Author : Rosebell Paul and Shilpa M
Abstract :
The high surge in the number of devices connected by the Internet of Things (IoT) causes several challenges to the security of data and users, leaving the Internet open to various threats. IoT networks faces several challenges that call for the evolution of traditional internet topology. Network security has recently become more important due to the significant damage that DDoS poses to it. DDoS assaults are now frequent as cyber threats because of the expansion of IoT devices, their complexity, and the use of attack services. A DDoS attack prevents actual internet users from using the suspect's services. IoT device failures and data theft are being caused more frequently by DDoS attacks on IoT devices. In response to this growing threat, new techniques are being developed to identify and halt attack traffic from IoT botnets. Recent anomaly detection experiments using machine learning (ML) have demonstrated its potential to identify malicious Internet traffic. Unreliable customer IoT devices have been used to perform distributed denial of service (DDoS) attacks against crucial Internet infrastructure botnets like Mirai to launch distributed denial of service (DDoS) assaults against vital Internet infrastructure. A distributed denial-of-service (DDoS) attack is a malicious attempt to delay a server, service, or its working system with an excessive volume of Web traffic. By using numerous compromised computer systems as sources of attack traffic, DDoS attacks are made effective. Computers and other networked resources, like as IoT devices, can be exploited machines. This promotes the development of novel methods to immediately identify consumer IoT attack traffic. In this study, we use a variety of machine learning classifiers to identify DDoS attacks coming from botnet-infected IoT devices.
Keywords :
DDoS attack, IoT devices, Machine learning classifier
