<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-07-08T08:44:08Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/EAE28BBD-BDA4-4CD0-B97A-A6B2659964E1" ns1:id="EAE28BBD-BDA4-4CD0-B97A-A6B2659964E1"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/8EC1A3AB-E3EE-4024-B879-5B375039264C" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/BA5C6E86-61C3-42E5-8F7A-CDC80006093A" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/BA5C6E86-61C3-42E5-8F7A-CDC80006093A" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2025-11-30T00:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/1EC5254F-7320-46DA-A2D5-229569A83416" ns1:rel="FUND" ns1:start="2024-12-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10136899</ns2:identifier></ns2:identifiers><ns2:title>Unlocking multi-party fraud intelligence sharing with diverse datasets</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Grant for R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>Our project tackles the societal and economic challenge of stopping scams by enabling banks, payment providers, and telecom companies to exchange sensitive financial intelligence securely, based off a wide range of data formats. Fraud costs the UK &amp;pound;7 billion annually, with significant economic and societal impacts.

Verifoxx specializes in privacy-enhancing technologies (PETs). Our core product allows companies to share sensitive intelligence without exposing underlying data, ensuring secure data sharing between companies.

Our proposal addresses a challenge we currently have which is integrating our prototype with different data formats. We transform these data formats on the client's local end into a new format, which other companies can then query using Zero Knowledge Proofs. Currently, we are limited to structured numerical data like SQL tables and JSON, but it's critical to integrate diverse formats like Excel, Word, and PDFs to meet client needs, and help share fraud intelligence.

We will use the award to recruit a Large Language Model developer who will build a robust enrichment engine pipeline to handle various data formats seamlessly, increasing our data integration capabilities by 60%. This pipeline will include the following features:

* LLM Agent for Schema Extraction: Extracts schemas from structured and unstructured data sources.
* Data Processor: Integrates and processes data from diverse sources, including SQL databases, NoSQL databases, PDFs, Word documents, images, and Excel spreadsheets.

We have already validated the need to cater for diverse datasets with real customers in financial institutions, but we know this need will exist in other sectors too, meaning this feature is critical for us to achieve our market potential.

Regulators like the ICO endorse privacy-enhancing technologies because they allow for secure data sharing while protecting personal information. This regulatory support underscores the importance and potential of our project in ensuring privacy and security.

Winning this award will help our business grow by expanding the features of our product, growing our team and increasing the speed at which we can launch in market. It also gives us the opportunity to leverage an incredible package of business support to ensure we make the right decisions in scaling our business and finding the right investors.</ns2:abstractText></ns2:project>