Featurespace gets funding from the UK and US governments to prevent fraud

The privacy enhancing technologies (PETs) Challenge Prize funding enables Featurespace to develop privacy-preserving solutions that allow AI models to be trained on sensitive private data, important for revealing criminal activity, without organisations having to reveal, share, or combine their raw data. The company will apply cutting-edge federated deep learning incorporating privacy-enhancing techniques such as k-anonymity and local differential privacy to tackle financial crime.

The need for such an innovative tech solution is timely, as financial crime that impacts businesses, society, and consumers is likely to rise due to the expected global recession and the cost of living crisis in 2023, as per the press release. Trade body UK Finance predicts an ‘epidemic of fraud’ happening, due to increases in authorised push payment (APP) fraud, which totalled GBP 580 million lost in 2021, representing a 40% year-on-year increase in this type of crime. Additionally, the United Nations estimates that money laundering costs up to USD 2 trillion each year, undermining economic prosperity and financing organised crime.

Fighting fraud with AI and collaboration

Featurespace’s officials stated that the UK and US governments want banks to work together to stop fraud and money laundering. This type of privacy-preserving collaborative AI is a hard problem that they aim to solve and are confident they can meet this challenge. Featurespace’s solution is intended to help PSPs and banks tackle financial crimes including cross-border money laundering, application fraud, and APP fraud.

What is PETs aim?

Launched in July 2022, by Innovate UK, the UK's innovation agency, and National Science Foundation in the US, the scheme has awarded prize challenges to unleash the potential of PETs to combat global societal challenges. The first track, aimed at transforming financial crime prevention, will spur technological innovation to tackle the challenge of international money laundering.

This PETs project, which is backed by the international payments organisation SWIFT, can be harnessed to facilitate privacy-preserving financial information sharing and collaborative analytics, allowing anomalous payments to be identified without compromising the privacy of individuals.

Summing up the aims of the project, representatives from Featurespace added that a successful outcome of this project is to make money laundering across borders and between banks much more difficult. If you make it harder to launder money, you make criminal activities less profitable. This will benefit businesses, society, and consumers.

Featurespace now has until 24 January to build its AI prototype. If successful, the company’s solution will be showcased at the second Summit for Democracy in the US.