Biography

I am a Principle AI Research Engineer at CyberDesk, working on the intersection of AI and identity-centric data control. Previously I obtained my PhD at the Joint Academy of Doctoral Studies (JADS) launched between Imperial College London and Technical University of Munich. During my PhD I worked on topics such as privacy-preserving machine learning, attacks on collaborative machine learning, adversarial robustness, federated learning and memorisation in ML.

Some of my highlighted works include gradient-based model inversion attacks on collaboratively trained computer vision models (ACM TOPS 2023), low-cost empirical defences against privacy adversaries (PoPETS 2022), a framework for trustworthy collaborative medical image analysis (Nature Machine Intelligence 2021) and an overview of the current state of PPML and attacks on CML (Nature Machine Intelligence 2021).

Before that I was a Senior Privacy Researcher at Huawei Research (privacy, security and robustness of AI agents and LLMs). I was also a Machine Learning Researcher at Microsoft Research (memorisation and factuality in differentially private LLMs for healthcare) and Brave Research (efficient data and client selection in federated learning). Prior to that I was a Privacy Researcher at Oblivious (differentially private SQL and synthetic data) and OpenMined (differentially private deep learning for healthcare). Outside of all that cool privacy and AI stuff I am a rower (mostly retired, now a casual marathon runner) and a WSET-certified expert in beer (no retirement planned any time soon).