Mary Scott
Data Scientist
Mary joined IDDO in January 2025 as a Data Scientist to perform large-scale individual patient data meta-analyses, methods development, and statistical modelling to optimise the treatment of infectious disease. Her research will focus on improving the diagnosis and triage of patients with suspected severe malaria.
In February 2025, Mary defended her PhD thesis, titled “Differentially Private Methods for Releasing Aggregated Multi-Dimensional Messages”. She holds a Bachelor of Science in Mathematics from the University of Warwick.
Recent publications
Distributed, communication-efficient, and differentially private estimation of KL divergence
Preprint
Scott M. et al, (2024)
Towards Robust Federated Analytics via Differentially Private Measurements of Statistical Heterogeneity
Preprint
Scott M. et al, (2024)
ggregation and Transformation of Vector-Valued Messages in the Shuffle Model of Differential Privacy
Preprint
Scott M. et al, (2022)
ggregation and Transformation of Vector-Valued Messages in the Shuffle Model of Differential Privacy
Journal article
Scott M. et al, (2022), IEEE Transactions on Information Forensics and Security, 17, 612 - 627
pplying the Shuffle Model of Differential Privacy to Vector Aggregation
Preprint
Scott M. et al, (2021)