New research suggests that AI (artificial intelligence) techniques can be used to root out the scammers who con money out of users of dating apps.
An AI-powered neural network looked at a series of user profiles, studying user messages and the images they posted on authentic dating platforms, to improve chances of separating the lonely hearts from the hackers.
Taking into account members’ ages, gender and ethnicity, and the ways in which users described themselves in their profiles, the AI technology was able to identify fraudsters in 93% of cases, the research found.
Tricking dating app users out of money is an established practice among certain elements of the online criminal community; people in the UK lost around £50 million to financial love cheats in 2018, according to the UK’s police reporting centre, Action Fraud. Out of the victims surveyed, around 63% were women.
IT engineers in Britain, the US and in Australia collaborated to create the new AI system, which discovered that men (60%) were most likely to be putting the phoney profiles together, and that the average cheat was 50 years-of-age.
The AI technology honed in on the language employed by the sweet-talking cyber swindlers, with “emotive” words such as “caring”, “passionate” and “loving” commonly woven into profile blurbs.
The free-to-use Dating ‘N More platform was the subject of the AI training, where algorithms were built using the data of around 15,000 profiles. The website was chosen because Dating ‘N More publicly posts fake profiles when they are found.
The team behind the AI project are working towards the creation of a warning system that can alert date-seekers to fraudulent profiles at the earliest point possible. Typically, scammers lurking on dating sites have been tricky to track down and bring to justice, because profiles are usually made by individuals, and not part of automated or large-scale criminal projects.
The researchers said:
“We aim to more broadly examine the available data on online dating fraud, seeking information actionable for enforcement and other countermeasures.”
Join our free-to-attend digital event, Last Thursday in Privacy, addressing data protection, privacy and security challenges including working from home, COVID-19, global regulations and more. Visit https://digital.privsec.info/.
We have been awarded the number 1 GDPR Blog in 2019 by Feedspot.