Abstract
The proliferation of Internet of Things (IoT) systems and smart digital devices, has perceived them targeted by network attacks. Botnets are vectors buttoned up which the attackers grapple the control of IoT systems and comportment venomous activities. To confront this challenge, efficient machine learning and deep learning with suitable feature engineering are suggested to detect and protect the network from such vulnerabilities in the future. For the efficient detection of cyber attacks, the representative dataset shall be well-structured for training the model and then validating the proposed system to develop an optimal security model. In this research, we used the UNSW-NB15, a new IoT-Botnet dataset (a noisy and imbalanced dataset) to classify cyber-attacks. K-Medoid sampling and scatter search-based feature engineering techniques are used to obtain a representative dataset with optimal feature subsets. To validate the proposed methodologies, three most recent machine learning (ML) methods including (i) JChaid*- a recent upgrade version to Chi-square automatic interaction detection (CHAID) decision tree-based, (ii) A2DE (a semi-naive Bayesian averaged two-dependence estimator), & (iii) HGC- a hybrid of Genetic algorithm with K-means clustering and two deep learning (DL) methods such as (i) Deep Multilayer perceptron (DMLP) & (ii) Convolutional neural network (CNN) based classifiers are employed. From the extensive experimental analysis, it is pronounced that scatter search-based DMLP classifier outperforms the other competing models in terms of (i) highest detection rate with100% accuracy, 100% macro-averaged precision, 100% macro-averaged recall & 100% macro-averaged F1-score and (ii) low computational complexity with the least training time of 4.7 seconds & testing time of 0.61 seconds.
Highlights
Network attacks or intrusions are collections of events transmitted through network packets that pose a threat to the confidentiality, availability, and integrity of the Internet of Things (IoT) network, for the incapability of today's firewalls mechanism to detect and block such a current cybersecurity attack scenario
The results obtained with the use of scatter search and deep learning methods (DMLP and Convolutional neural network (CNN)) are encouraging with 100% micro-averages to precision, recall, and F1-score which makes them promising for most correctly identifying the threats in IoT botnet scenario
Since deep learning-based classifiers (DMLP and CNN) and hybrid K-means clustering and genetic algorithm (HGC) presents 100% accuracy, they were considered for comparisons with other existing works available to date
Summary
Network attacks or intrusions are collections of events transmitted through network packets that pose a threat to the confidentiality, availability, and integrity of the IoT network, for the incapability of today's firewalls mechanism to detect and block such a current cybersecurity attack scenario. With the extensive usage of smart digital devices in an IoT network environment, secure communications amongst such interconnected devices are the need of the day as the network vulnerabilities are complex and very costly to get removed from such an IoT network system. It is observed that an efficient network intrusion detection system could be able to detect modern security attacks, including zero-day attacks, and could prevent them from future occurrences. Network intrusion detection systems (NIDS) can be thought of either as misuse detection or anomaly detection. While many business organizations prefer to use misuse detection, anomaly detection is still considered an immature one, attracting many researchers to research anomaly detection.
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
