Anthony Hughes

Anthony Hughes

PhD Student, Computer Science
ajhughes3 at sheffield.ac.uk

I am pursuing my Ph.D. in Computer Science at the University of Sheffield, supported by a fully-funded UKRI scholarship.

Research: My PhD research investigates privacy in deep learning, focusing on how language models inadvertently leak sensitive information. I combine mechanistic interpretability with privacy research to understand and mitigate these vulnerabilities.

Recent work: My EMNLP 2025 paper investigates privacy leakage in abstractive summarisation. My EACL 2026 paper (Findings), developed during a research visit with the CrySP group at the University of Waterloo, uses circuit discovery to understand and patch PII leakage in language models. I'm currently exploring how mechanistic interpretability can be extended to defend against a broader range of attack vectors.

Past: I completed my MSc in Computational Linguistics (Distinction) from University of Wolverhampton, and my undergraduate degree in Computer Science (1st Class, Hons) from Nottingham Trent University. Before returning to academia, I spent 10 years in industry as a software engineer, progressing to Lead Software Engineer and NLP Engineer roles.

Selected Publications in Privacy

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
A Hughes, V Duddu, N Asokan, N Aletras, N Ma
EACL 2026 - Findings
How Private are Language Models in Abstractive Summarisation?
A Hughes, N Aletras, N Ma
EMNLP 2025 - Main Proceedings
Generative Byte-Level Models for Restoring Spaces, Punctuation, and Capitalization in Multiple Languages
L Dyer, A Hughes, et al.
Practical Solutions for Diverse Real-World NLP Applications 2023

Selected Publications in Health/Medicine

Large Language Models to Improve Understanding of Radiology Reports
S Alabed et al. including A Hughes.
The Lancet Digital Health
Identifying and Aligning Medical Claims Made on Social Media with Medical Evidence
A Hughes, Xingyi Song
LREC-COLING 2024
Understanding Inflicted Injuries in Young Children: Toward an Ontology-based Approach
F Maikore et al. including A Hughes
EKAW 2024

Research Experience

Visiting Graduate Researcher
Cryptography, Security and Privacy Group (CrySP), University of Waterloo
July 2025 - September 2025

Collaborators/Mentors: Vasisht Duddu, N. Asokan. Research on mechanistic approaches to understanding PII leakage in language models.

Industry Experience

Lead Software Engineer / NLP Engineer
Data Language
January 2014 - Current

Led development of NLP-based products including automated text classification SaaS, data visualization tools, and integration of language models into data platforms. Built production systems serving FTSE clients.

Software Engineer
Ontoba
June 2013 - June 2014

Software Engineer working on services solving data silo issues with linked data.

Software Engineer (Internship)
Press Association
July 2011 - September 2012

Worked on a new digital platform centered around semantic web technologies.

Education

PhD Computer Science
University of Sheffield, 2024 - Current
PgDip Speech and Language Technologies
University of Sheffield, 2023 - 2024
MSc Computational Linguistics (Distinction)
University of Wolverhampton, 2021 - 2023
BSc Computer Science (1st Class, Hons)
Nottingham Trent University, 2009 - 2013

Selected Awards

UKRI PhD Scholarship
University of Sheffield, 2023-2027
NIHR/BRC Sheffield Funding
£1,650, April 2025 - September 2025
Best Poster
Insigneo Showcase, July 2025