Applying Deep Learning to Enhance Physical Unclonable Functions

  • Applying Deep Learning to Enhance Physical Unclonable Functions

+ Project Title

Applying Deep Learning to Enhance Physical Unclonable Functions

+ Project Description

Imagine a world in which everyone owns self-driving cars, you can use a mobile phone to control home alarm/heating/lighting systems and remotely see your GP with wearable devices providing your health data. This will all be possible within the next decade with the advent of the Internet of Things (IoT), when all our devices will be connected to the Internet and each other. However, in order for IoT to be successful, ensuring the privacy and security of the information communicated between devices is crucial and is a major challenge. Practical attacks of IoT devices have already been shown, e.g. 150,000 IoT devices were compromised for use in the massive distributed denial-of-service attack that recently disrupted US internet traffic. As IoT devices typically have limited memory and computing power, adding complex security features is not always possible.


This research will investigate the design of novel Physical Unclonable Functions, which exploit random variations found in the silicon used in the manufacture of electronic chips as an inherently lightweight means to uniquely identify and authenticate IoT devices. Some PUF designs are susceptible to machine learning based modelling attacks. Therefore this research will investigate techniques to build novel PUF solutions that are resistant to such approaches, and will also consider using deep learning approaches to enhance toe security and resilience of PUF designs.

+ Academic Requirements

A minimum 2.1 honours degree or equivalent in Electrical and Electronic Engineering or relevant degree is required.


This is a GCHQ-sponsored PhD studentship; therefore, only UK nationals are eligible for this funding.

GCHQ will be offering the student an opportunity to work more closely with them – e.g., via a short secondment or attendance at technical meetings. As such, the recipient of this studentship will have to be appropriately security cleared by GCHQ before they start their doctoral studies.

+ General Information

This GCHQ-sponsored PhD studentship provides funding for 3.5 years and commences in September 2019. It covers approved tuition fees and a maintenance grant of approx.. £22,500 each year (tax-free). A further £5k of funding will also be available per annum for travel to conferences, collaborative partners, GCHQ visits, etc.


Applicants should apply electronically through the Queen’s online application portal at:

Deadline for submission of applications is 31 May 2019.
(Early submission of applications is recommended)

+ Contact Details

Supervisor Name: Máire O’Neill                   Tel: 028 90971785

QUB Address: ECIT, QUB                     Email: / Web: