Funding

Self-funded

Project code

COMP7580423

Department

School of Computing

Start dates

October, February and April

Application deadline

Applications accepted all year round

Applications are invited for a self-funded, 3-year full-time or 6-year part time PhD project.

The PhD will be based in the School of Computing and will be supervised by Dr Rahim Taheri.

The work on this project could involve:

  • SDN Security
  • Reinforcement learning applications in IDS
  • Adversarial attacks and defences

Software de麍ned networking (SDN) has become a novel network architecture and design by employing manageable software between the control and data planes. The separation of data plane and control plane in SDN reduces the complexity of network devices and provides a flexible network management. Since switches in the data plane do not have any intelligence, they just send raw data packets to the controller. Unfortunately, this behaviour introduces a serious vulnerability which can be used by attackers to overload the controller through a large number of flow requests.

 Machine Learning-based intrusion detection system (IDS) is often used by the SDN controller to detect and process network attacks. However, a major gap in this area is the lack of real-time information gathering from the environment by the IDS. It arises from the nature of current data flow steering, as only the SDN controller is responsible for handling the flows among the switches. This affects the performance and QoSs. To accomplish this, this project will apply a stream of reinforcement learning (RL) methods in IDS. In this architecture, the IDS receive network traffic from the SDN-switches through control layer and returns the classification to the environment. An RL-based agent searches the environment in real-time and determines the necessary security policies based on the properties of the environment that are always changing and applies them to the SDN controller. The controller implements these policies on the switches, and this loop is constantly repeating itself.

In summary, the following objectives have been set for this project:

  • To design an architecture to model the RL on server-based IDS in an SDN system 
  • To design a RL for high volume of data to help IDS decision
  • To design an Adversarial attack/defense in IDS-SDN

Entry requirements

You'll need a good first degree from an internationally recognised university or a Masters degree in an appropriate subject. In exceptional cases, we may consider equivalent professional experience and/or qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

N/A

How to apply

We encourage you to contact Dr Rahim Taheri (Rahim.taheri@port.ac.uk) to discuss your interest before you apply, quoting the project code below.

When you are ready to apply, please follow the 'Apply now' link on the Computing PhD subject area page and select the link for the relevant intake. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our How to Apply page offers further guidance on the PhD application process. 

When applying please quote project code:COMP7580423