You are not logged in
Time stamp: 20:39:20-27/5/2024


Machine learning model to identify attacks on IoT device.

Afnan Naif N Al Hazmi


Supervised by Amir Javed; Moderated by Michael Daley

The project aims to build a machine learning model to identify an ongoing cyberattack on IoT devices. The ML model will be built by analysing a publicly available labelled dataset . The project will be carried out in three stages : Stage 1 1.Downloading and cleaning of the dataset. This will require you to download captured pcap file of malicious traffic. 2.Transforming the dataset into a machine-readable format. Stage 2 By using a programming language build unsupervised machine learning model. Then optimise the model by changing different parameters of the model. Testing the model using k-fold validation techniques and then testing it on an unseen dataset. Stage 3 Discuss your results and your finding.

Below are the desirable aims of the project 1.Building another ML model that can not only identify an ongoing malicious attack but also categorise them into different kind of attacks, by showing different clusters that form. 2.Build a GUI to show how a network packet can be classified into malicious or benign and thus demonstrate how you can detect an ongoing attack.

If you are interested in this project what I want you to do is 1.Drop me an email confirming your interest. 2. Answer below mentioned questions. 1. What is your interpretation of the problem area? What is the specific problem you will address? 2. Which methods will you use to address the problem? 3. Will your project be research-focussed (answer a question) or implementation-focussed (provide a product)? 4. Which tangible outcome(s) will we have at the end? 5. How does your knowledge and skill set align with this project?

Final Report (05/11/2021) [Zip Archive]

Publication Form