Aydin Abadi, Steven Murdoch and Mohammad Naseri

CDEI, Innovate UK, NIST and NSF

Privitar and University of Cardiff

STARLIT was a collaboration between Privitar, UCL and Cardiff University on applying privacy-preserving federated machine learning to financial crime prevention. The resulting system was entered to the Privacy Enhancing Technologies prize challenge, led by the U.K.’s Centre for Data Ethics and Innovation (CDEI) and Innovate UK, the U.S. National Institute of Standards and Technology (NIST), and the U.S. National Science Foundation (NSF), in cooperation with the White House Office of Science and Technology Policy.

The system employs machine learning to analyse information about the transactions and parties involved without collecting all of the data in one place. STARLIT tested the system using synthetic data provided by SWIFT. The system was announced as joint first place winners at the Summit for Democracy, alongside the University of Cambridge. The team were also honoured with a special recognition prize for their work.

Further information can be found on the PETs Prize Challenge website and UCL’s press release on the award.


Abadi A, Doyle B, Gini F, Guinamard K, Murakonda SM, Liddell J, Mellor P, Murdoch SJ, Naseri M, Page H, Theodorakopoulos G, Weller S. Starlit: Privacy-Preserving Federated Learning to Enhance Financial Fraud Detection, arXiv preprint 2401.10765, January 2024.