PhD

PhD student project showcase in CyberASAPY8 Demo Day

A group of PhD students: Yaxiong Lei and Zihang Zhang, in our school have been awarded a CyberASAP project. This is funded by the Department of Science, Innovation, and Technology (DSIT) and organised by InnovateUK. CyberASAP aims to fund innovative cybersecurity solutions from academics. Their project, LockEyeGaze, confronts the cybersecurity challenge of sophisticated computer vision and 3D modelling technologies such as deepfake and AI-generated tampering. They are leveraging the dynamic patterns of eye movements for security, which are significantly more difficult to replicate than static biometric features like static face, iris and fingerprints. Their project is selected to present at CyberASAP Year 8 Demo Day in Canary Wharf, London today.

Links:

https://web-eur.cvent.com/event/4a986031-294f-4ad0-9a9b-a4863690bd19/summary

https://iuk-business-connect.org.uk/events/cyberasap-year-8-demo-day/

PhD Viva Success: Thomas Hansen

On behalf of the School, we would like to congratulate Thomas Hansen supervised by Dr Edwin Brady who has successfully defended his thesis.

Thanks to Dr Adam Barwell who was internal examiner and Dr Jeremy Yallop from University of Cambridge as external examiner.

Many congratulations to Thomas! 🎉

 

PGR Seminar with Mustafa Abdelwahed and Maria Andrei

The next PGR seminar is taking place this Friday 6th December at 2PM in JC 1.33a

Below is a title and Abstract for Mustafa and Maria’s talks – Please do come along if you are able.

Mustafa Abdelwahed:

Title: Behaviour Planning: A toolbox for diverse planning

Abstract:

Diverse planning approaches are utilised in real-world applications like risk management, automated streamed data analysis, and malware detection. These approaches aim to create diverse plans through a two-phase process. The first phase generates plans, while the second selects a subset of plans based on a diversity model. A diversity model is a function that quantifies the diversity of a given set of plans based on a provided distance function.

Unfortunately, existing diverse planning approaches do not account for those models when generating plans and struggle to explain why any two plans are different.

Existing diverse planning approaches do not account for those models when generating plans, hence struggle to explain why any two plans are different, and are limited to classical planning.

To address such limitations, we introduce Behaviour Planning, a novel toolbox that creates diverse plans based on customisable diversity models and can explain why two plans are different concerning such models.

Maria Andrei: 

Title: Leveraging Immersive Technology to Enhance Climate Communication, Education & Action

Abstract: Climate change represents one of the most pressing challenges of our time, not only in its environmental impacts, but also as a pivotal science communication problem. Despite widespread scientific consensus on the causes and mitigation strategies for climate change, public understanding remains deeply fragmented and polarized. This disconnect hinders the collective action required from individuals, organizations, and policymakers to combat global warming effectively. My research explores the potential of immersive technologies to bridge the gap between scientific knowledge and public understanding by leveraging experiential learning experiences to inspire the attitudinal and behavioural shifts necessary to address climate change.

PGR Seminar with Zhongliang Guo

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

Below is a title and Abstract for Zhongliang’s talk– Please do come along if you are able.

Title: Adversarial Attack as a Defense: Preventing Unauthorized AI Generation in Computer Vision

Abstract: Adversarial attack is a technique that generate adversarial examples by adding imperceptible perturbations to clean images. These adversarial perturbations, though invisible to human eyes, can cause neural networks to produce incorrect outputs, making adversarial examples a significant security concern in deep learning. While previous research has primarily focused on designing powerful attacks to expose neural network vulnerabilities or using them as baselines for robustness evaluation, our work takes a novel perspective by leveraging adversarial examples to counter malicious uses of machine learning. In this seminar, I will present two of our recent works in this direction. First, I will introduce the Locally Adaptive Adversarial Color Attack (LAACA), which enables artists to protect their artwork from unauthorized neural style transfer by embedding imperceptible perturbations that significantly degrade the quality of style transfer results. Second, I will discuss our Posterior Collapse Attack (PCA), a grey-box attack method that disrupts unauthorized image editing based on Stable Diffusion by exploiting the common VAE structure in latent diffusion models. Our research demonstrates how adversarial examples, traditionally viewed as a security threat, can be repurposed as a proactive defense mechanism against the misuse of generative AI, contributing to the responsible development and deployment of these powerful technologies.

AI Seminar Wednesday 27th November – Lars Kotthoff

We have another exciting AI seminar coming up on Wednesday 27th November at 1pm.

This time our speaker is an alumnus!

When? 27/11/24, 1pm

Where? JCB 1.33B

Who? Lars Kotthoff

Lars Kotthoff is the Templeton Associate Professor of Computer Science, Founding Adjunct Faculty at the School of Computing, and a Presidential Faculty Fellow at the University of Wyoming. His research in foundational AI and Machine Learning as well as applications of AI in other areas (in particular Materials Science) has been widely published and recognized. Lars is a senior member of the Association for the Advancement of AI and the Association of Computing Machinery.

What?

Title: AI for Materials Science: Tuning Laser-Induced Graphene Production

Abstract: AI and machine learning have advanced the state of the art in many application domains. We present an application to materials science; in particular, we use surrogate models with Bayesian optimization for automated parameter tuning to optimize the fabrication of laser-induced graphene. This process allows to create thin conductive lines in thin layers of insulating material, enabling the development of next-generation nano-circuits. This is of interest for example for in-space manufacturing. We are able to achieve improvements of up to a factor of two compared to existing approaches in the literature and to what human experts are able to achieve, in a reproducible manner. Our implementation is based on the open-source mlr and mlrMBO frameworks and generalizes to other applications.

PGR Seminar with Carla Davesa Sureda

The next PGR seminar is taking place this Friday 22nd November at 2PM in JC 1.33a

Below is a Title and Abstract for Carla’s talk – Please do come along if you are able.

Title:

Towards High-Level Modelling in Automated Planning

Abstract:

Planning is a fundamental activity, arising frequently in many contexts, from daily tasks to industrial processes. The planning task consists of selecting a sequence of actions to achieve a specified goal from specified initial conditions. The Planning Domain Definition Language (PDDL) is the leading language used in the field of automated planning to model planning problems. Previous work has highlighted the limitations of PDDL, particularly in terms of its expressivity. Our interest lies in facilitating the handling of complex problems and enhancing the overall capability of automated planning systems. Unified-Planning is a Python library offering high-level API to specify planning problems and to invoke automated planners. In this paper, we present an extension of the UP library aimed at enhancing its expressivity for high-level problem modelling. In particular, we have added an array type, an expression to count booleans, and the allowance for integer parameters in actions. We show how these facilities enable natural high-level models of three classical planning problems.

Doughnuts will be available! 🍩

Fully funded PhD scholarship in Algorithms for Data Science

Lead supervisor: Dr Peter Macgregor

Application deadline: 1 March 2025

Project description:

Modern data science and machine learning applications involve datasets with millions of data points and hundreds of dimensions. For example, deep learning pipelines produce massive vector datasets representing text, image, audio and other data types. The analysis of such datasets with classical algorithms often requires significant time and/or computational resources which may not be available in many applications.

This motivates the development of a new generation of fast algorithms for data analysis, running in linear or sub-linear time and often producing an approximate result rather than an exact one. Moreover, the dataset may change over time, requiring dynamic algorithms which handle updates efficiently.

This project will tackle aspects of the design, analysis, and implementation of algorithms for processing large dynamic datasets, with the aim to develop new algorithms with state-of-the-art practical performance and/or theoretical guarantees. This could involve performing new analysis of existing algorithms, designing new algorithms with provable guarantees, or implementing heuristic algorithms with state-of-the-art empirical performance.

Possible Directions

Potential areas of research, depending on the interests of the candidate include:

  • Developing improved nearest-neighbour search algorithms (e.g., based on kd-trees, HNSW, locality-sensitive hashing).
  • Exploring any connection between hierarchical clustering algorithms and nearest-neighbour search algorithms.
  • Creating new dynamic or hierarchical clustering algorithms (e.g. based on spectral clustering or DBSCAN).
  • Creating dynamic algorithms for numerical linear algebra. For example, maintaining the PCA of a dynamically changing dataset.
  • Any other project in the area of algorithmic data science and machine learning.

Applicants should have a strong interest in the mathematical analysis of algorithms, knowledge of topics in discrete mathematics and linear algebra, and some familiarity with existing algorithms for data analysis and machine learning. Strong programming skills would also be desirable.

The scholarship:

We have one fully-funded scholarship available, starting in September 2025. The scholarship covers all tuition fees irrespective of country of origin and includes a stipend valued at £19,705 per annum. More details of the scholarship can be found here: https://blogs.cs.st-andrews.ac.uk/csblog/2024/10/24/phd-studentships-available-for-2025-entry/, but please note the different application deadline.

Eligibility criteria:

We are looking for highly motivated research students keen to be part of a diverse and supportive research community. Applicants must hold a good Bachelor’s or Master’s degree in Computer Science, or a related area appropriate for the topic of this PhD.

International applications are welcome. We especially encourage female applicants and underrepresented minorities to apply. The School of Computer Science was awarded the Athena SWAN Silver award for its sustained progression in advancing equality and representation, and we welcome applications from those suitably qualified from all genders, all races, ethnicities and nationalities, LGBT+, all or no religion, all social class backgrounds, and all family structures to apply for our postgraduate research programmes.

To apply:

Interested applicants can contact Peter Macgregor with an outline proposal.

Full instructions for the formal application process

The deadline for applications is 1 March 2025.

AI Seminar Tuesday 19th November – Francesco Leofante

The School is hosting an AI seminar on Tuesday 19th November at 11am in JCB1.33A/B

Our speaker is Francesco Leofante from Imperial College London.

Title:

Robustness issues in algorithmic recourse.

Abstract:

Counterfactual explanations (CEs) are advocated as being ideally suited to providing algorithmic recourse for subjects affected by the predictions of machine learning models. While CEs can be beneficial to affected individuals, recent work has exposed severe issues related to the robustness of state-of-the-art methods for obtaining CEs. Since a lack of robustness may compromise the validity of CEs, techniques to mitigate this risk are in order. In this talk we will begin by introducing the problem of (lack of) robustness, discuss its implications and present some recent solutions we developed to compute CEs with robustness guarantees.

Bio:

Francesco is an Imperial College Research Fellow affiliated with the Centre for Explainable Artificial Intelligence at Imperial College London. His research focuses on safe and explainable AI, with special emphasis on counterfactual explanations and their robustness. Since 2022, he leads the project “ConTrust: Robust Contrastive Explanations for Deep Neural Networks”, a four-year effort devoted to the formal study of robustness issues arising in XAI. More details about Francesco and his research can be found at https://fraleo.github.io/.

PGR Seminar with Daniel Wyeth and Ferdia McKeogh

The next PGR seminar is taking place this Friday 15th November at 2PM in JC 1.33a

Below is a Title and Abstract for Daniel’s and Ferdia’s talks – Please do come along if you are able.

Daniel:

Deep Priors: Integrating Domain Knowledge into Deep Neural Networks

Deep neural networks represent the state of the art for learning complex functions purely from data.  There are however problems, such as medical imaging, where data is limited, and effective training of such networks is difficult.  Moreover, this requirement for large datasets represents a deficiency compared to human learning, which is able harness prior understanding to acquire new concepts with very few examples.  My work looks at methods for integrating domain knowledge into deep neural networks to guide training so that fewer examples are required.  In particular I explore probabilistic atlases and probabilistic graphical models as representations for this prior information, architectures which enable networks to use these, and the application of these to problems in medical image understanding.

Ferdia:

“Lessons Learned From Emulating Architectures”

Automatically generating fast emulators from formal architecture specifications avoids the error-prone and time-consuming effort of manually implementing an emulator. The key challenge is achieving high performance from correctness-focused specifications; extracting relevant functional semantics and performing aggressive optimisations. In this talk I will present my work thus far, and reflect on some of the unsuccessful paths of research.

Doughnuts will be available! 🍩