School of Computer Science and Statistics
Risk detection models (such as IBM’s Granite Guardian) are increasingly used to flag harmful prompts and responses in large language model pipelines. These systems are trained on human and synthetic data to identify risks across multiple dimensions, but their reliability and fairness are not guaranteed. They may over-flag certain groups, miss subtle harms, or be … Read more
This project investigates how post-hoc counterfactual explanations can be used to debug opaque models such as deep neural networks by revealing which feature changes most influence predictions. In applications like anomaly detection, counterfactuals help clarify why certain cases are flagged as abnormal and expose when models rely on spurious correlations or biased patterns. By using … Read more
Project Description: Optical fibre networks are critical to global connectivity, yet they are susceptible to accidental damage or deliberate tampering. While distributed acoustic sensing (DAS) has been widely investigated for disturbance detection, an alternative approach relies on monitoring the state of polarisation (SOP) of light propagating in the fibre. The SOP is highly sensitive to … Read more
Project Description: Recent advances in distributed fibre sensing have shown that existing optical fibre cables, originally deployed for telecommunications, can also serve as dense sensor arrays. By sending probe signals through the fibre and analysing the backscattered light, it is possible to extract information about environmental changes such as vibrations, temperature, and strain along the … Read more
Project Description: The exploration of quantum communication protocols for entanglement distribution is critical to advancing secure and efficient quantum networks. Entanglement, a unique quantum phenomenon, enables instantaneous correlations across vast distances, which is essential for applications like quantum key distribution (QKD) and quantum teleportation. In particular, quantum teleportation is an essential feature of quantum networks … Read more
Project Description: Over the past few years, telecommunications networks have migrated towards concepts of virtualisation and programmability, which has recently also affected the optical layer [1]. This has provided the opportunity to build more intelligent control of optical networks, for example to predict quality of transmission and thus improve overall network utilisation, as transmission channels … Read more
The current Internet architecture assumes communication based on the identity of hosts e.g. the name/IP address of a webserver in a URL. Individual clients connect to specific servers to retrieve documents and videos. Information-centric networking instead assumes that content is the focus of communication and is uniquely named in networks e.g. a consumer asks a … Read more
Matrix multiplication is one of the commonly-used computations across a wide range of applications. For example, most implementations of neural networks implement very large numbers of matrix multiplications. Almost all processor and GPU manufacturers provide libraries with carefully hand-tuned fast matrix multiplication routines. All the best-known algorithms matrix multiplication are out-of-place; that is, the result … Read more
Many cryptographic schemes rely on modular arithmetic. Modular arithmetic is a system of arithmetic operators on integers where the numbers “wrap around” back to zero when they reach a value called the modulus. For example, if our modulus is 17, then (12 + 14) mod 17 = 9. When we implement modular arithmetic, a key … Read more
ELIGIBILITY: This project is for a student taking the online MSc in Statistics and Data Science. Survival analysis refers to models and methods for survival data, that is, data on the failure of a system. Usually this takes the form of times when failure occurs, with the failure referring to events like the system no … Read more