Research projects in Information Technology

Modern Intel, ARM and AMD CPUs offer hardware support for trusted execution environments (TEEs). A TEE protects the confidentiality and integrity of computation and data by shielding it from the rest of the system. Due to its practical performance , TEEs have been widely used in plenty of scenarios and systems to secure the data processing. However, TEEs suffer side-channel attacks that can break their security guarantees. 

Project description: 

Project description: On behalf of the Victorian Orthopaedic Trauma Outcomes Registry (VOTOR), we will establish the role of artificial intelligence (AI) deep learning to improve the prediction of clinical and longer-term patient-reported outcomes following distal radius (wrist) fractures. The PRAISE study will, for the first time, use a flexible three-stage multimodal deep learning fracture reasoning system to unlock important information from unstructured data sources including X-ray images, surgical and radiology text reports.

Student satisfaction with feedback is consistently low in higher education, and there is a lack of understanding regarding how students interpret and interact with feedback. Learning analytics promises to enhance feedback practice by providing real-time data and insights into learning behaviour and outcomes, so as to inform educational interventions. However, the feedback loop remains open without an understanding of how students make use of the received feedback or the #sustainability of such feedback practice.

This project aims to explore techniques for characterising the complexity of statistical models. By complexity we refer to the ability of a model to learn patterns, and to potentially generalise to new unseen data. Interest in this are has recently resurged due to the discovery of phenomena such as "double descent", and the use of new model types such as deep neural networks, which challenge traditional notions of complexity.

This PhD project is funded by a DHCRC project "Actionable data for clinicians and external accreditors in support of quality care provision and continuous accreditation". The successful applicant will work as part of a larger research team on this project which includes multiple industry partners.

Bangladesh has seen a sharp rise in active-users of the internet (especially of social media) and of mobile technology over the last decade. With rising internet penetration, more of the relatively underprivileged communities are getting access to ICT directly or indirectly. However, the skyrocketing growth of digital access has not been matched with a growth in digital literacy, which means that grass-roots communities have not been able to use this new resource to support their economic and social ventures and improve their situation.

The United Nations Development Programme has identified access to information as an essential element to support poverty eradication. People living in poverty are often unable to access information that is vital to their lives, such as information on their entitlements, public services, health, education or work opportunities. Timely access to information is essential to perform many economic, social and leisure activities. In today’s digital age, information is more and more often provided in digital form.

Complex questions are those that involve discrete, aggregate operators that operate on numbers (min, max, arithmetic) and sets (intersection, union, difference). Recent advances in complex question answering take a neural-symbolic approach and combine meta-learning and reinforcement learning techniques [1,2,3]. On the other hand, the generation of complex questions, the dual problem, is less explored. Recent works on knowledge graph question generation [4,5] have mainly focussed on multi-hop questions.

Model checking is an automated formal verification technique in which, given a property F – typically represented as a temporal logic formula – and a model of a system M, one checks whether the system M satisfies property F. Model checking is a well understood formal verification technique supported by several tools, many of which are available online. A little less is known about probabilistic model checking.