Samuel Maddock
About Me
I am a final-year PhD student supervised by Prof. Graham Cormode and Prof. Carsten Maple (WMG). Before starting my PhD I graduated with a first-class MEng in Discrete Mathematics here at the University of Warwick.
Research Interests
My research interests lie at the intersection of computer security, data privacy and machine learning. I am mainly interested in the area of privacy-preserving machine learning (PPML) which seeks to develop ML algorithms to learn privately and securely from data which is often highly distributed. This includes areas such as Differential Privacy (DP), Federated Learning (FL) and Federated Analytics.
News
- [April 2026] I have joined Electric Twin as a Research Engineer working on synthetic audiences and behavioural modelling.
- [Sept 2025 – March 2026] Part-time Research Collaborator @ Meta AI: Generative modelling for tabular data.
- [September 2025] Attending VLDB 2025 @ London, UK; presenting our tutorial on "Synthetic Tabular Data: methods, attacks and defences".
- [August 2025] Attending KDD 2025 @ Toronto, Canada; presenting our tutorial on "Synthetic Tabular Data: methods, attacks and defences"
- [Summer 2025] Research Scientist Intern @ Meta AI, Menlo Park, CA: Interning in the Central Applied Science (CAS) team, supervised by Shripad Gade. Working on large-scale missing data imputation.
-
[May 2024 – May 2025]: Part-time Research Collaborator @ Meta AI: Scaling private synthetic tabular data.
- [August 2024] Attending KDD 2024 @ Barcelona; presenting our work on "FLAIM: AIM-based Synthetic Data Generation in the Federated Setting"
- [May 2023] Attending ICLR 2023 @ Kigali; presenting our work on "CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning".
- [December 2022] Attending CCS 2022 @ Los Angeles; presenting our work "Federated Boosted Decision Trees with Differential Privacy".
-
[Summer 2022] Research Intern @ Meta AI, Paris: Empirical privacy measurement in federated learning. Supervised by Pierre Stock and Alexandre Sablayrolles.
Conference Publications
- Samuel Maddock, Graham Cormode, Carsten Maple. "FLAIM: AIM-based Synthetic Data Generation in the Federated Setting", In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '24) (Slides, Poster)
- Samuel Maddock, Alexandre Sablayrolles and Pierre Stock. "CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning". The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. (Slides, Poster)
- Samuel Maddock, Graham Cormode, Tianhao Wang, Carsten Maple and Somesh Jha. "Federated Boosted Decision Trees with Differential Privacy". In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (CCS ’22), November 7–11, 2022, Los Angeles, CA, USA. (Slides)
- Graham Cormode, Samuel Maddock, and Carsten Maple. "Frequency estimation under local differential privacy." Proceedings of the VLDB Endowment 14.11 (2021): 2046-2058. (Slides , Poster)
Workshop Papers
- [Spotlight] Samuel Maddock, Shripad Gade, Graham Cormode, Will Bullock, "Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation", SynthData Workshop @ ICLR 2025
- Samuel Maddock, Shripad Gade, Graham Cormode, Will Bullock. "GEM+: Scalable State-of-the-Art Private Synthetic Data with Generator Networks", TPDP 2026
Preprints
- Samuel Maddock, Graham Cormode, Carsten Maple. "Private Federated Multiclass Post-hoc Calibration", arXiv
Accepted Tutorials
- Tutorial @ KDD 2025 Toronto, Canada: Synthetic Tabular Data: methods, attacks and defenses, Graham Cormode, Samuel Maddock, Enayat Ullah, Shripad Gade,
- Tutorial @ VLDB 2025 London, UK: Synthetic Tabular Data: methods, attacks and defenses, Graham Cormode, Samuel Maddock, Enayat Ullah, Shripad Gade,
Invited Talks & Service
- Trustworthy Synthetic Data in Practice (TSDiP) @ Alan Turing Institute (2024)
- WPCCS'23 (Awarded 'Best in Session')
- FLOW Seminar: CANIFE (2023)
- Google FL Workshop (2022)
- Invited Reviewer: KDD 2024, NeurIPS 2024, ICLR 2025, ICML 2025, NeurIPS 2025, ICLR 2026, NeurIPS 2026
Teaching
I have been a teaching assistant for the following modules:
