Postgraduate

PGR Seminar – Sharon Pisani & Mirza Hossain

The next PGR seminar is taking place this Friday 3rd October 11:00-12:00 in JC 1.33A.

Below are the Titles and Abstracts for Sharon and Mirza’s talks – Please do come along if you are able.

Sharon Pisani

Title: Building Sustainable Heritage Virtual Museums for Communities using Sociodata

Abstract: Virtual museums are moving beyond simple digitisation of artefacts to become dynamic platforms for community engagement and sustainable development. This talk introduces the VERA Platform, which combines a flexible Virtual Museum Infrastructure with a new layer of sustainability-oriented contextual data called sociodata. Sociodata links heritage objects to their cultural landscapes, local communities, and relevant Sustainable Development Goals, enabling richer discovery, analysis, and reuse. In this talk, I will outline the platform’s architecture and metadata model. The talk will highlight technical challenges such as interoperability with European data spaces, and supporting interactive storytelling at scale—issues highly relevant to digital infrastructure and data-driven research in the heritage sector.

Bio: Sharon is a PhD researcher examining the role of emergent digital technologies in preserving and engaging with cultural heritage while supporting sustainable development. Her research focuses on digitising cultural landscapes—both natural and cultural heritage—to assess various impacts on heritage and community identities. She explores how digital tools, including 3D scanning, 3D modeling, and mixed reality, can aid in recreating and safeguarding heritage at risk.

Mirza Hossain

Title: Fishing for monosemantic neurons in histopathology foundation models

Abstract: This early-stage study introduces Histoscope, an interactive system for examining sparse autoencoders (SAEs) that are trained on top of the UNI pathology encoder. Vision transformers for histopathology often exhibit superposition, where single neurons respond to multiple distinct tissue patterns, making interpretation difficult. Histoscope provides quantitative metrics and visualisations to assess whether neurons are monosemantic—associated with a single concept—or polysemantic—associated with multiple concepts. The work highlights methods for analysing internal representations of histopathology foundation models and contributes to efforts toward more transparent AI in pathology.

Bio: Mirza Hossain is a second-year PhD candidate in Computer Science at the University of St Andrews. His research focuses on multimodal AI in medical imaging with an emphasis on mechanistic interpretability of large foundation models. He is supervised by Dr. David Harris-Birtill.

 

Research Activities by Open Virtual Worlds Research Group

Throughout July, the research group Open Virtual Worlds from the School of Computer Science was involved in digitalising the archaeological artefacts, historical sites, and natural landscapes in collaboration with their important partner, Timespan Museum in Helmsdale, Highlands.

Two PhD students, Junyu Zhang and Sharon Pisani, who are researching digital heritage and sustainability, were using 360 photogrammetry to document the local area, which included the Helmsdale Harbour, the former fish curing yards, the Jurassic Coast, the Flow Country UNESCO World Heritage Site, and other natural reserves.

The efforts and work from the Open Virtual Worlds will contribute to the HERITALISE project, which includes seventeen partners from seven different European countries – the Netherlands, Italy, Spain, Belgium, Scotland, Malta, and Cyprus, forming an interdisciplinary group to bring about intelligence, methodology and expertise towards the preservation and promotion of cultural heritage.

old and new harbours in Helmsdale

old and new harbours in Helmsdale

old and new harbours in Helmsdale

old and new harbours in Helmsdale

outdoor fieldwork at natural reserve sites, historical landscapes and heritage ruins

outdoor fieldwork at natural reserve sites, historical landscapes and heritage ruins

members from Open Virtual World and Timespan Museum

members from Open Virtual World and Timespan Museum

members from Open Virtual World and Timespan Museum

Interviews with descendants of historical heritage site

3D scanning of archaeological artefacts

3D scanning of archaeological artefacts

Helmsdale

🎉Award Congratulations to Dr Di Wu – IEEE IoT PhD Thesis Competition 🎉

Congratulations to Dr Di Wu for an outstanding achievement of third place in the inaugural IEEE  IoT PhD thesis competition. Di’s thesis, “Distributed Machine Learning on Edge Computing Systems” truly stood out among the impressive nominations. The judging panel, comprising leading experts in the field, meticulously evaluated each submission based on the following criteria: Problem Definition, Design Methodology, Achievement and Significance, Originality and Innovation, Impact, and Quality of Presentation. Di’s work exemplified excellence across these critical areas.

Congratulations once again to Di on this well-deserved recognition for advancing the field of IoT! 🎉

PhD Student Tai Nguyen Wins Best Paper Award at GECCO 2025

Tai Nguyen, supervised by Dr. Nguyen Dang (University of St Andrews) and Dr. Carola Doerr (CNRS Researcher, Sorbonne Université, France), has been awarded the prestigious Best Paper Award at GECCO 2025, held in Málaga, Spain, from July 14–18, 2025. GECCO (Genetic and Evolutionary Computation Conference) is the leading international conference in its field, known for its highly competitive acceptance rate (36% in 2025).
The award-winning paper is titled: “On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+(λ,λ))-GA.” link: https://dl.acm.org/doi/10.1145/3712256.3726395

To help a general audience understand the significance of this work, here is a brief and simplified summary:

This research tackles a central challenge in Artificial Intelligence (AI) and optimization. Imagine trying to complete a complex task by finding the best possible strategy, which often involves tuning many parameters—a process known as “algorithm configuration.” Now, imagine an intelligent AI assistant that not only helps determine the best settings for the task at hand but also adapts those settings as the task evolves. This is known as “Dynamic Algorithm Configuration” (DAC). Tai’s work applies Reinforcement Learning (RL), a powerful AI technique in which computers learn to make decisions by receiving “rewards” or “penalties” based on their actions. The paper’s key insight is that the design of the reward system plays a crucial role in enabling the AI assistant to learn effectively, particularly in dynamic or complex environments. If rewards are not carefully crafted, the AI may struggle to identify effective strategies, especially as problem sizes increase. To address this, the team developed methods for designing reward functions, which significantly improved the AI’s learning speed and performance. In essence, their approach allows the AI to find optimal solutions much more efficiently than existing techniques.

Congratulations to Tai Nguyen, Dr. Nguyen Dang, Dr. Phong Le (University of St Andrews), Dr. André Biedenkapp (University of Freiburg, Germany), and Dr. Carola Doerr (Sorbonne Université, France) on this outstanding achievement! Party popper

Enhancing Privacy for Internet Communication Protocols: SICSA 2025 Best PhD Dissertation Award

On June 25th, recent PhD graduate, Dr. Gregor Haywood, took to the stage to receive the 2025 “Best PhD Dissertation” award from the Scottish Informatics & Computer Science Alliance (SICSA).

Gregor (Lecturer in the Department of Cybersecurity and Computing at Abertay University, and PhD Award Recipient) is standing next to Debbie Meharg, Head of Applied Informatics at Edinburgh Napier University, Director of Education for SICSA, and the Awards Chair for the SICSA PhD Conference 2025

Gregor (Lecturer in the Department of Cybersecurity and Computing at Abertay University, and PhD Award Recipient) standing next to Debbie Meharg, Head of Applied Informatics at Edinburgh Napier University, Director of Education for SICSA, and the Awards Chair for the SICSA PhD Conference 2025

Haywood’s thesis on “Enhancing Privacy for Secure Internet Communications Using ILNP” focuses on how underlying communication protocols for the Internet could avoid privacy leaks, while continuing to utilise existing and unmodified hardware, infrastructure, and Internet services. His study was driven by his academic interest in the unintended design consequences within large interconnected systems:

I was captivated by working on a project that was socially relevant, deeply technical, and – ultimately – solvable. During my undergraduate degree, I started looking at private communication mechanisms as a side project which turned into my fourth year dissertation, and continued onwards within my PhD. I like finding these unanticipated problems, such as privacy leaks, security vulnerabilities, and environmental impacts, then designing new solutions that fix the problems without disrupting the operation of the larger systems at play.

(Dr Gregor Haywood)

Professor Saleem Bhatti (School of Computer Science, Thesis Supervisor) adds how Haywood’s work demonstrates what he believes to be ‘the first deployable mechanisms for perturbing traffic flow correlation attacks at the network level, as well as perturbing privacy attacks by traffic analysis as might be performed by a machine-learning system.’ For this reason, he was enthusiastic to nominate Haywood’s thesis for SICSA stating it is ‘an excellent balance between science and engineering’ that explores ‘a radical new architecture in addressing using the Identifier Locator Network Protocol (ILNP) to provide new privacy features, and an open-source implementation in FreeBSD that is usable across the existing Internet.’

The SICSA PhD Conference is a flagship event that brings together various participants from fourteen Scottish Universities to network, seek graduate researcher training, and share current interdisciplinary projects.  Dr. Tristan Henderson (Senior Lecturer and Computer Science Director of Postgraduate Research) comments that submitting to awards like SICSA encompasses the primary aim of a PhD which is ‘learning how to become a researcher.’  For this reason, SICSA is a valuable opportunity that allows for ‘visibility’ and ‘recognition’ of one’s work both nationally and internationally adds Professor Bhatti.

In recalling his own researcher journey, Dr. Haywood expresses that whether it is learning a ‘can-do attitude’ from his supervisor or picking up fun new quirks such as ‘hoarding hand-me-down computer hardware,’ the School of Computer Science and his PhD research have given him the space to thrive for who he is:

I suspect I will always have a compulsive need to understand things deeply – but now I have the tools to harness that into computer systems research, and whether it is celebrating the wins at conference dinners with my peers, or consoling each other at the pub when it falls apart, it is hard to put words to the joy I have found in being part of a community that can match my passion, debate my technical points, and jump on board with my research tangent conversation starters.

 It’s also very exciting to celebrate a success in privacy research. Many headlines are about data breaches and privacy failures, and so much research is about finding new privacy vulnerabilities. Being able to say “we made things better” is a great opportunity to inject some hope into the research community.                                            

(Dr Gregor Haywood)

This elation also extends to the pride that both Dr. Henderson and Professor Bhatti feel towards having an alumnus from the School of Computer Science win this award. ‘It is a great honour’ they both expressed, and a fantastic example of the impact of research outside of the university. Dr. Henderson adds that within Computer Science, there are a number of dissertation awards, including SICSA and the BCS in the UK, as well as the ACM internationally. He encourages students to indulge in these opportunities, with Dr. Haywood noting that ‘participating in this and other inter-institutional networking events was a valuable way for me to broaden my research mindset throughout the PhD’ and if you are considering applying yourself or nominating a student for it, ‘do it! You have nothing to lose and plenty to gain. Remember it is the reviewers’ job to judge your work, not yours – you just need to judge whether you have time to submit.’

Dr. Haywood is now a Lecturer in the Department of Cybersecurity and Computing at Abertay University with key aspects of his work being available to read online until his thesis is published in June 2026.

ILNP web page: https://ilnp.cs.st-andrews.ac.uk

Blog written by Nina Globerson

PGR Seminar: Xinya Gong

The next PGR seminar is taking place this Friday 20th June at 2PM in JC 1.33a

Below are the Title and Abstract for Xinya’s talk – Please do come along if you are able.

Title: Invisible Health Clues in Everyday Handwriting

Abstract: Everyday handwriting may quietly reflect subtle changes in a person’s health. This project explores how natural writing patterns—such as stroke dynamics, pressure, and rhythm—can offer early indicators of motor or neurological conditions. Without relying on wearables or clinical tasks, the approach passively monitors handwriting during familiar, routine activities. By capturing and analyzing writing behaviour over time, it becomes possible to build personal baselines and detect meaningful deviations. This work envisions a privacy-preserving, low-effort way to integrate long-term health awareness into daily life.

PGR Seminar – Kyren Fox + Zipei Li

The next PGR seminar is taking place this Friday 13th June at 2PM in JC 1.33a

Below are the Titles and Abstracts for Kyren and Zipei’s talks – Please do come along if you are able.

Kyren Fox

Title: Privacy and Trust on the Web

Abstract: Many web users use content blockers to block ads and privacy invasive trackers from the sites they visit. Due to their increasing popularity and the nature of a web funded by ads and tracking, ad-tech firms have resorted to more and more sophisticated countermeasures to evade these blocks that have created an arms race between the blockers and trackers. Since many content blockers rely on community curated filter-lists that require laborious manual review, combined with the increasingly dynamic obfuscation techniques utilised by trackers to evade these blocks, issues surrounding the scalability of content blockers have arisen.

While many automated solutions have been proposed to assist in blocking unwanted privacy-harming functionality, there is still no comprehensive solution that tackles all privacy-invasive behaviours, avoids breaking legitimate website functionality, and is robust to evasion techniques. Existing solutions all have trade-offs but do not appear to offer the user any control over what trade-off they wish to make. This project will seek to demonstrate that it is possible to give users control over the granularity of trade-off they wish to make that will satisfy the trade-offs in a scalable and robust manner for their use case.

Zipei Li

Title: Understanding the Planning Capabilities and Limitations of LLMs in Blocks World.

Abstract: We investigates the planning capabilities of Large Language Models (LLMs) in the symbolic Blocks World domain. While prior work has shown that LLMs often fail to generate correct or executable plans, we shift focus toward understanding the causes of plan failures and identifying the conditions under which LLMs succeed. We evaluate a range of LLMs across problems of varying difficulty and four prompt types with varying degrees of information in natural language. To support this analysis, we introduce a fine-grained failure category spanning Plan, Goal, State, and Action. The analysis deepens our understanding of LLM planning behavior and contributes an empirical framework for diagnosing failure modes, thereby informing the development of more reliable LLM-based planning systems.