Cyberattacks Detection in IoT-Based Smart City Applications Using Machine Learning Techniques

Abstract

In recent years, the widespread deployment of the Internet of Things (IoT) applications has contributed to the development of smart cities. A smart city utilizes IoT-enabled technologies, communications and applications to maximize operational efficiency and enhance both the service providers’ quality of services and people’s wellbeing and quality of life. With the growth of smart city networks, however, comes the increased risk of cybersecurity threats and attacks. IoT devices within a smart city network are connected to sensors linked to large cloud servers and are exposed to malicious attacks and threats. Thus, it is important to devise approaches to prevent such attacks and protect IoT devices from failure. In this paper, we explore an attack and anomaly detection technique based on machine learning algorithms (LR, SVM, DT, RF, ANN and KNN) to defend against and mitigate IoT cybersecurity threats in a smart city. Contrary to existing works that have focused on single classifiers, we also explore ensemble methods such as bagging, boosting and stacking to enhance the performance of the detection system. Additionally, we consider an integration of feature selection, cross-validation and multi-class classification for the discussed domain, which has not been well considered in the existing literature. Experimental results with the recent attack dataset demonstrate that the proposed technique can effectively identify cyberattacks and the stacking ensemble model outperforms comparable models in terms of accuracy, precision, recall and F1-Score, implying the promise of stacking in this domain.

Cyber Threat Predictive Analytics for Improving Cyber Supply Chain Security

“…Another initiative [24] explores the viability of using machine learning approaches to predict power systems disturbance and cyberattack discrimination classifiers and focuses specifically on detecting cyberattacks where deception is the core tenet of the event [24][25][26][27][28][29][30]. The authors in [24] evaluated the classification performances on, NNge, OneR, SVM, RF, JRpper and Adaboost algorithms to learn the dataset and focused specifically on detecting cyber attacks where deception is the core tenet of the event.…”

IoT-based smart cities: a bibliometric analysis and literature review

“…Data security and privacy (Al-Turjman et al, 2019;Gheisari et al, 2019;Shen et al, 2019) Cyberattacks detection (Alrashdi et al, 2019;Li et al, 2019;Qureshi et al, 2020;Rashid et al, 2020) Blockchain (Fan et al, 2020;Gong et al, 2019;Yetis & Sahingoz, 2019) 5 Data Data management and analysis (Cheng et al, 2018;He et al, 2018;Mohbey, 2017;Moreno-Cano et al, 2015;Romero et al, 2016;Zahmatkesh & Al-Turjman, 2020;Zhang, 2020) Engineering Management in Production and Services fication of potential threats. They also allow adapting particular functions to the user's individual preferences.…”

“…As Gheisari et al (2019) claimed, the main drawbacks of the methods used to protect data privacy from IoT devices are the simultaneous transmission of whole data, the use of a single static privacy-preserving method for the whole system, and the lack of understanding of the context of a situation. Besides general research on systems, methods, and tools for security and privacy, authors often address the use of blockchain technology (Fan et al, 2020;Gong et al, 2019) and the prevention and detection of cyberattacks (Alrashdi et al, 2019;Qureshi et al, 2020;Rashid et al, 2020).…”

Application of Deep Learning for Quality of Service Enhancement in Internet of Things: A Review

“…With the advent of big data technologies, various IoT-based services have emerged to make use of this data. Smart manufacturing [5,21,22,49,50], smart cities [24,51], smart homes [6,7], smart agriculture [52][53][54], and smart health [8,17,[55][56][57], among others, have undergone tremendous development with the aid of deep-learning techniques. IoT basedservices today are faced with an unprecedented surge in generated sensory data, which comes in different formats, structures, and semantics.…”