Cybersecurity Threat Detection in Smart Cities using Box Plot Sampling Isolation Forest

Now a days, the standard of living in urban areas is advanced by leveraging technologies such as Cyber-Physical Systems (CPS) and Internet of Things (IoT) with physical infrastructures. However, smart cities highly rely on digital ecosystems, which makes them vulnerable to various cyber threats such as Distributed Denial of Service (DDoS) which leads in violations of privacy and threats to safety of citizens. To develop an effective and efficient system for detection of cybersecurity threats, Box plot Sampling Isolation Forest (BSIF) is proposed. Initially, the data was collected from the Botnet Traffic attack in Internet of Things (BoT_IoT) dataset which contains various normal traffic and Botnet traffic data. After that, Label Encoding (LE) was used for preprocessing the data, which assigns numerical labels to each category in the dataset. Furthermore, Recursive Feature Elimination (RFE) technique was utilized for iterative extraction and selection of features based on their weights is performed by Decision Tree (DT). Finally, the proposed BSIF model is used for detection of cybersecurity threats associated with smart cities, by leveraging box plot sampling method. The proposed obtain better results with 99.74% Precision, 99.92% Accuracy, 99.87% Recall and 99.84% F1-score, compared with Smart Attacks Learning Machine Advisor (SALMA) respectively.