<?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/2CAF0516-BFA5-4927-A7B8-CA37B0AC98FF" ns1:id="2CAF0516-BFA5-4927-A7B8-CA37B0AC98FF"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/5A80BB5D-9B29-4A08-9E35-447CCA0B7B58" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/5A80BB5D-9B29-4A08-9E35-447CCA0B7B58" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2020-12-31T00:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/A7E18FCB-6D22-42F7-A315-C277CF404616" ns1:rel="FUND" ns1:start="2019-01-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">104873</ns2:identifier></ns2:identifiers><ns2:title>Thirdfort - Data driven property fraud prevention</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>ISCF</ns2:leadFunder><ns2:abstractText>&amp;quot;In 2018, property fraud is a &amp;pound;120million problem in the UK, almost 20 times worse than it was in 2015\. It affects all sizes of law firm and property transaction values. Law firms are increasingly having to spend time and resources to fend off cyber-attacks, with the Government's National Cyber Security Centre finding over 80% of law firms were on the receiving end of cyber-attacks in 2018\.

We are building an AI driven algorithm that can be used by property lawyers to detect fraudulent property transactions in real time, protecting property buyers, sellers and lawyers. Aside from monetary loss, property fraud is devastating law firms and their reputations. The problem is widespread, fast-growing and an enormous stress for property lawyers -- with over 90% of the 150 property lawyers we've spoken telling us fraud was their number one fear during property transactions.

Transaction specific fraud data gathered from law firms such as Mishcon de Reya and others recently hit by fraud will form the training data for our AI algorithm. From this data we can identify the typical characteristics of a fraudulent transaction. For future transactions, our AI will process a range of specific transaction data and compare it to the identified characteristics of fraudulent transactions. Our AI system can then generate a real-time risk score for property lawyers before the fraud is committed. When money is stolen, people are losing life-shattering amounts without recourse. Typical examples of property fraud include a first-time buyer losing their &amp;pound;100,000 deposit via email misdirection; or a property owner who has their identify stolen and their tenanted flat 'hijacked' and sold to an unsuspecting seller. Fraud attempts are costly and painful to prevent or reverse for both property lawyers and consumers. Our AI algorithm will accurately calculate the risk for every transaction, allowing additional checks to be completed where necessary, and giving peace-of-mind to both property lawyers and their clients.&amp;quot;</ns2:abstractText></ns2:project>