Analysis of Machine Learning Techniques for Anomaly Detection in the Internet of Things

Brady, Shane; Magoni, Damien; Murphy, John; Assem, Haytham; Portillo-Dominguez, A. Omar

doi:10.1109/la-cci.2018.8625228

Cited by 13 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study in [ 47 ] uses machine learning approaches to investigate the identification of anomalies in the IoT context. It makes use of two datasets for time-series data and databases such as the NSL-KDD dataset for non-time-series data.…”

Section: Machine Learning—iot Network Anomaly Detectionmentioning

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

Section: Machine Learning—iot Network Anomaly Detectionmentioning

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

show abstract

“…In the comparative study executed by Brady et al (2018), kNN, Logistic Regression (LR), Linear Discriminant Analysis (LDA), Decision Tree (CART), and Naïve Bayes (NB) were the machine feature reduction, the maximum accuracy achieved in real-time detection was 80 percent. This was impressive in its regard; however, recent research have surpassed this accuracy.…”

Section: Machine Learning Applications With Many Features Make Traini...mentioning

confidence: 99%

Botnet Detection in IoT Devices Using Random Forest Classifier with Independent Component Analysis

Akash

Rouf

Jahan

et al. 2022

Journal of Information and Communication Technology

View full text Add to dashboard Cite

With rapid technological progress in the Internet of Things (IoT), it has become imperative to concentrate on its security aspect. This paper represents a model that accounts for the detection of botnets through the use of machine learning algorithms. The model examined anomalies, commonly referred to as botnets, in a cluster of IoT devices attempting to connect to a network. Essentially, this paper exhibited the use of transport layer data (User Datagram Protocol- UDP) generated through IoT devices. An intelligent novel model comprising Random Forest Classifier with Independent Component Analysis (ICA) was proposed for botnet detection in IoT devices. Various machine learning algorithms were also implemented upon the processed data for comparative analysis. The experimental results of the proposed model generated state-of-the-art results for three different datasets, achieving up to 99.99% accuracy effectively with the lowest prediction time of 0.12 seconds without overfitting. The significance of this study lies in detecting botnets in IoT devices effectively and efficiently under all circumstances by utilizing ICA with Random Forest Classifier, which is a simple machine learning algorithm.

show abstract

“…Their results showed that a neighbor comparison and historical comparison are useful to predict anomalies within their proposed algorithm. Moreover, in [13] the authors evaluated some techniques suitable to identify realtime anomalies within an IoT network with the aim of offering practitioners a reference about when such techniques might be more appropriate.…”

Section: Related Workmentioning

confidence: 99%

Choosing Machine Learning Algorithms for Anomaly Detection in Smart Building IoT Scenarios

Almaguer-Angeles

Murphy

et al. 2019

2019 IEEE 5th World Forum on Internet of Things (WF-IoT)

Self Cite

View full text Add to dashboard Cite

Internet of Things (IoT) systems produce large amounts of raw data in the form of log files. This raw data must then be processed to extract useful information. Machine Learning (ML) has proved to be an efficient technique for such tasks, but there are many different ML algorithms available, each suited to different types of scenarios. In this work, we compare the performance of 22 state-of-the-art supervised ML classification algorithms on different IoT datasets, when applied to the problem of anomaly detection. Our results show that there is no dominant solution, and that for each scenario, several candidate techniques perform similarly. Based on our results and a characterization of our datasets, we propose a recommendation framework which guides practitioners towards the subset of the 22 ML algorithms which is likely to perform best on their data.

show abstract

Analysis of Machine Learning Techniques for Anomaly Detection in the Internet of Things

Cited by 13 publications

References 11 publications

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

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

Botnet Detection in IoT Devices Using Random Forest Classifier with Independent Component Analysis

Choosing Machine Learning Algorithms for Anomaly Detection in Smart Building IoT Scenarios

Contact Info

Product

Resources

About