Privacy-preserving collaborative AI
What has to hold, technically and institutionally, for federated analysis across sensitive datasets to be trustworthy rather than merely decentralised?
Institutions that cannot pool sensitive data can still learn together, if the governance is built alongside the method.
Federated learning is often presented as a privacy guarantee. It is better understood as a change in where the risk sits. Moving computation to the data removes one exposure and introduces others: attribution that shifts with modelling choices, updates that leak, and a governance question about who is accountable when no single party holds the dataset.
I work on both halves of that, the technical behaviour of federated methods under audit, and the institutional arrangements that make a federation legible to a regulator or a ministry.
Selected work
- PaperBA-FedSHAP: A reproducible toolkit for auditing background-induced attribution driftAuthor, SSRN2026
- SoftwareBA-FedSHAP, auditing background-induced attribution driftAuthor2026
- PolicyFederated learning for children's data: encoding trust in education systemsAuthor, UNICEF Innocenti, Office of Strategy and Evidence2025
Next / Territory
Human-centred adaptive systems