My research project is focused on developing a knowledge-based model for Intrusion Detection within the security domain. This direction is a shift from the prevalent data-driven methods in the field. Despite their effectiveness in detection, these methods are often...
My research project is focused on developing a digital twin of the financial markets that can be used by various participants (such as banks, asset managers, investors, etc.) to assess the impact of deploying AI systems into the markets and by financial regulators to...
The main aim of my research project is to further the understanding of uncertainty quantification in probabilistic machine learning systems. Specifically, the project is focused on better understanding the validity, and extending the scope, of the practice of...
When reasoning and planning, humans make use of a wealth of semantic knowledge: place a human in a new house and ask them to make a coffee and they will instinctively search out the kitchen, locate a kettle, etc. We know how to do this as we have acquired a rich set...
I work on extracting interpretable and symbolic representations from noisy neural representations of data. I believe being able to understand and trust our AI systems can enable many exciting applications of AI and alleviate the risks of deploying systems we...
My PhD focuses on combining temporal logic with causality to improve the verification of AI systems. This will allow us to express interventional (“what will happen if…?”) and counterfactual (“what would have happened if…?”) queries as logical formulae, allowing us to...
Exploration in Reinforcement Learning (RL) has been a well-researched topic since the inception of RL, with a plethora of methods proposed that aim to perform “good” exploration, which is often measured by “regret”; the difference between the...
My research involves using the Interactive Theorem Prover, Isabelle/HOL, to formalise matching algorithms. Using a theorem prover allows you to provide formal guarantees about the efficacy of an algorithm. The focus of my research is on matching algorithms used in...
My PhD project focuses on detecting deception and manipulation in AI systems. The goal is to build tools and methods that can have a real-world impact on the regulation of these technologies. There is a very real possibility that the algorithms that are being (and...
I research the mathematics and computational theory behind voting. Specifically, I look at voting systems in which there can be multiple winners, and so ideally we would like voting systems which produce outcomes where voters are proportionally represented in the...
My research interests lie in the intersection of software engineering and AI. My research aims to improve code generation with LLM by using rule-based approaches, such as knowledge graphs. It focuses on enhancing the compliability, correctness, and explainability of...
My project focuses on advancing the concept of Reward Machines (RMs) in reinforcement learning. In particular, I aim to design algorithms to learn RMs in a noisy setting and apply them in real-world scenarios. Reward Machines are inherently interpretable, which helps...