Privitar to lead “Project STARLIT” with University College London and Cardiff University to advance the use of privacy-enhancing technologies in financial fraud prevention
Privitar, the leader in modern data provisioning, has been selected as a Phase 1 winner in the UK-U.S. PETs Prize Challenge, a transatlantic innovation prize challenge created by the United Kingdom and United States governments to advance the use of privacy-enhancing technologies (PETs) in tackling some of our most pressing societal challenges, including preventing financial crime and bolstering pandemic response.
Privitar is advancing to phase 2 of the challenge, where the company will lead a collaboration with University College London and Cardiff University to advance their proposal for “Project STARLIT” to create an end-to-end privacy-preserving federated learning solution that tackles the challenge of international money laundering.
“Financial crime is a massive, global challenge that costs as much as $2 trillion each year, according to UN estimates,” said Dr. Suzanne Weller, Head of Research at Privitar, and Project STARLIT lead researcher. “Privacy-enhancing technologies have an important role in finding more successful approaches to detecting fraud, while at the same time protecting individual’s sensitive financial information.”
“Privacy-enhancing technologies have an important role in finding more successful approaches to detecting fraud, while at the same time protecting individual’s sensitive financial information.”
Privitar’s project STARLIT will focus on improving the accuracy of algorithms by enabling more collaboration between financial institutions. As more information is pieced together about the accounts and transactions involved, a clearer understanding emerges of the patterns and characteristics that indicate fraud. However, linking together this information results in more context for each transaction and each account, which can increase privacy risk by providing more possibilities to recognize individuals in the dataset and reveal their sensitive information.
Building upon Privitar’s data security and privacy platform, which enables effective and responsible data use, Project STARLIT will focus on offering a safer way to analyze data held across different financial institutions. The accuracy of crime detection can be improved without collecting and centralizing data in one place. By integrating federated learning, the team will derive predictive features from the data to train a machine learning model without organizations having to reveal, share, or combine their raw data. The prototype will enable collaborative analysis while preventing confidential information from being shared across financial institutions to limit any information that can be learned about innocent individuals from the deployment of machine learning models.
Read More: How to Drive Engagement and Fuel Sales with NFTs with These Best Practices in 2023
“Privacy-enhancing technologies enable organizations to harness the power of data in a way that protects privacy, and facilitates collaboration,” added Jason du Preez, Privitar CEO. “There is incredible potential in the use of these technologies to tackle financial crimes and to help transform financial fraud prevention overall. We’re delighted to advance to the next phase of this competition, alongside the data privacy leaders from the United States and the United Kingdom, to create innovative solutions that will mature and broaden their adoption.”
The UK-U.S. Privacy Enhancing Technology (PET) Prize Challenge challenges were developed as part of a joint effort between the United Kingdom and the United States, and are being 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. Winning solutions will have the opportunity to be profiled at the second Summit for Democracy, to be convened by President Joe Biden, in early 2023.