Document Type



This item is available under a Creative Commons License for non-commercial use only



Publication Details

Dissertation submitted in partial fulfilment of the requirements of Dublin Institute of Technology for the degree of MSc. in Computing (Security and Forensics) 2017.


Internet of Things (IoT) is one of the fast growing technologies today. It is a technology by which billions of smart objects or devices known as “Things” can use several types of sensors to collect various types of data about themselves and/or the surrounding environment. They can then share this with authorized parties to serve several purposes such as controlling and monitoring industrial facilities or improving business service or functions. There are currently 3 billion devices connected to the Internet. The number will increase to 20 billion by 2020. While these devices make our life easier, safer and healthier, they are expanding the number of attack targets available to hackers. Therefore, protecting these devices from adversaries and unauthorized access and modification is very important. This research proposes a novel approach for anomalies detection in IoT systems based on a combination of two robust machine learning algorithms; inverse weight clustering (IWC) and C4.5 decision tree algorithm. IWC is an enhanced version of k-means algorithm that can be used to effectively cluster data into groups based on similarities between this data. C4.5 is a decision tree algorithm that can be used to build decision tree for classifying data. The proposed model was tested and evaluated, and the result demonstrates that the model is very accurate in detecting anomalies in IoT data.