Abstract
The Internet of Things (IoT) combines hundreds of millions of devices which are capable of interaction with each other with minimum user interaction. IoT is one of the fastest-growing areas in of computing; however, the reality is that in the extremely hostile environment of the internet, IoT is vulnerable to numerous types of cyberattacks. To resolve this, practical countermeasures need to be established to secure IoT networks, such as network anomaly detection. Regardless that attacks cannot be wholly avoided forever, early detection of an attack is crucial for practical defense. Since IoT devices have low storage capacity and low processing power, traditional high-end security solutions to protect an IoT system are not appropriate. Also, IoT devices are now connected without human intervention for longer periods. This implies that intelligent network-based security solutions like machine learning solutions must be developed. Although many studies in recent years have discussed the use of Machine Learning (ML) solutions in attack detection problems, little attention has been given to the detection of attacks specifically in IoT networks. In this study, we aim to contribute to the literature by evaluating various machine learning algorithms that can be used to quickly and effectively detect IoT network attacks. A new dataset, Bot-IoT, is used to evaluate various detection algorithms. In the implementation phase, seven different machine learning algorithms were used, and most of them achieved high performance. New features were extracted from the Bot-IoT dataset during the implementation and compared with studies from the literature, and the new features gave better results.
Highlights
Concerns over security and privacy regarding computer networks are increasing in the world, and computer security has become a requirement as a result of the spread of information technology in daily life
While we use the same Bot-Internet of Things (IoT) dataset presented in [9], we focus on extracting new features from the dataset and evaluating different machine learning algorithms on this dataset. [22] is another study that used the BoT-IoT dataset
As already noted in the previous sections, the major objective of the experiments is to evaluate the performance of machine learning algorithms in detecting IoT network attacks
Summary
Concerns over security and privacy regarding computer networks are increasing in the world, and computer security has become a requirement as a result of the spread of information technology in daily life. Along with a massive increase in the amount of information present in networks, faster and more effective methods of detection of attacks are required [2] and there is no doubt that there is scope for more progressive methods to improve network security In this context, in order to provide embedded intelligence in the IoT environment, we can consider Machine Learning (ML) as one of the most effective computational models. Some works use signature-based techniques to detect attacks [3], [7]; for instance, in the domain of network traffic analysis, [3] applied four different machine learning techniques as preliminary tools to learn the features of some known attacks.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
