IoT Anomaly Detection Using a Multitude of Machine Learning Algorithms

Balega, Maria; Farag, Waleed; Ezekiel, Soundararajan; Wu, Xin-Wen; Deak, Alicia; Good, Zaryn

doi:10.1109/aipr57179.2022.10092209

Cited by 2 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work, ML anomaly detection models for IoT were evaluated using the IoT-23 dataset [20], and the models were evaluated using the NSL-KDD dataset in another paper [21]. The present paper will extend these results to include more datasets.…”

Section: Related Workmentioning

confidence: 89%

Enhancing IoT Security: Optimizing Anomaly Detection through Machine Learning

Balega,

Farag,

et al. 2024

Electronics

Self Cite

View full text Add to dashboard Cite

As the Internet of Things (IoT) continues to evolve, securing IoT networks and devices remains a continuing challenge. Anomaly detection is a crucial procedure in protecting the IoT. A promising way to perform anomaly detection in the IoT is through the use of machine learning (ML) algorithms. There is a lack of studies in the literature identifying optimal (with regard to both effectiveness and efficiency) anomaly detection models for the IoT. To fill the gap, this work thoroughly investigated the effectiveness and efficiency of IoT anomaly detection enabled by several representative machine learning models, namely Extreme Gradient Boosting (XGBoost), Support Vector Machines (SVMs), and Deep Convolutional Neural Networks (DCNNs). Identifying optimal anomaly detection models for IoT anomaly detection is challenging due to diverse IoT applications and dynamic IoT networking environments. It is of vital importance to evaluate ML-powered anomaly detection models using multiple datasets collected from different environments. We utilized three reputable datasets to benchmark the aforementioned machine learning methods, namely, IoT-23, NSL-KDD, and TON_IoT. Our results show that XGBoost outperformed both the SVM and DCNN, achieving accuracies of up to 99.98%. Moreover, XGBoost proved to be the most computationally efficient method; the model performed 717.75 times faster than the SVM and significantly faster than the DCNN in terms of training times. The research results have been further confirmed by using our real-world IoT data collected from an IoT testbed consisting of physical devices that we recently built.

show abstract

Section: Related Workmentioning

confidence: 89%

Enhancing IoT Security: Optimizing Anomaly Detection through Machine Learning

Balega,

Farag,

et al. 2024

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly using the IoT-23 dataset, another study [ 56 ] explored the use of ML methods to enhance security in IoT systems. It focused on the application of the Gradient-Boosting and Extreme Gradient-Boosting (XGBoost) algorithms in identifying anomalous traffic.…”

Section: Machine Learning—iot Network Anomaly Detectionmentioning

confidence: 99%

“…Figure 4 includes a summary of the datasets most used in the studies considered for this study. According to Figure 4 among all of the datasets, UNSW-NB 15 and IoT-23 appear to be the most used datasets for both ML and DL model testing [ 56 , 63 ].…”

Section: Research Summarymentioning

confidence: 99%

Machine Learning and Deep Learning Techniques for Internet of Things Network Anomaly Detection—Current Research Trends

Rafique,

Abdallah,

Musa

et al. 2024

Sensors

View full text Add to dashboard Cite

With its exponential growth, the Internet of Things (IoT) has produced unprecedented levels of connectivity and data. Anomaly detection is a security feature that identifies instances in which system behavior deviates from the expected norm, facilitating the prompt identification and resolution of anomalies. When AI and the IoT are combined, anomaly detection becomes more effective, enhancing the reliability, efficacy, and integrity of IoT systems. AI-based anomaly detection systems are capable of identifying a wide range of threats in IoT environments, including brute force, buffer overflow, injection, replay attacks, DDoS assault, SQL injection, and back-door exploits. Intelligent Intrusion Detection Systems (IDSs) are imperative in IoT devices, which help detect anomalies or intrusions in a network, as the IoT is increasingly employed in several industries but possesses a large attack surface which presents more entry points for attackers. This study reviews the literature on anomaly detection in IoT infrastructure using machine learning and deep learning. This paper discusses the challenges in detecting intrusions and anomalies in IoT systems, highlighting the increasing number of attacks. It reviews recent work on machine learning and deep-learning anomaly detection schemes for IoT networks, summarizing the available literature. From this survey, it is concluded that further development of current systems is needed by using varied datasets, real-time testing, and making the systems scalable.

show abstract

IoT Anomaly Detection Using a Multitude of Machine Learning Algorithms

Cited by 2 publications

References 14 publications

Enhancing IoT Security: Optimizing Anomaly Detection through Machine Learning

Enhancing IoT Security: Optimizing Anomaly Detection through Machine Learning

Machine Learning and Deep Learning Techniques for Internet of Things Network Anomaly Detection—Current Research Trends

Contact Info

Product

Resources

About