Lecturer, University of Sydney
I started a new position as a Lecturer in Computer Science at the Univeristy of Sydney!
June 2026New paper on arXiv about clustering with private evolution
April 2026I will present our work on interpeting the error of private median queries at TPDP 2026 in Boston.
My research interests are at the intersection of privacy-enhancing technologies (PETs) and artificial intelligence (AI), with a focus on developing practical privacy-preserving systems for AI and data science. Specifically, I aim to enable the deployment of systems with meaningful privacy guarantees through strategic algorithmic design that improves privacy trade-offs and rigorous auditing that uncovers privacy oversights. My research spans the fields of differential privacy, secure computation, and evolutionary algorithms. To learn more about my research, check out my publications page!
I am currently a Lecturer in the School of Computer Science at the University of Sydney. Previously, I completed my PhD and Master’s degree at the University of Waterloo, where I worked with Florian Kerschbaum in the Cryptography, Security, and Privacy (CrySP) Lab. I have also interned at Microsoft Research with the Azure Research Security and Privacy group in Cambridge and the Algorithms Group in Redmond.
© 2026 Thomas Humphries
Website template by Spencer H. Bryngelson