Scientists have developed new artificial intelligence (AI) based computing algorithms for dating apps and websites that 'think' like humans to pinpoint fake profiles designed to con victims out of thousands of pounds. The researchers led by the University of Warwick in the UK developed the algorithms as part of wide-ranging research into combating online fraud.
The new algorithms have been designed specifically to understand what fake dating profiles look like and then to apply this knowledge when they scan profiles submitted to online dating services. They automatically look out for suspicious signs inadvertently included by fraudsters in the demographic information, the images and the self-descriptions that makeup profiles, and reach an overall conclusion as to the probability of each individual profile is fake.
When tested, the algorithms produced a very low false-positive rate -- the number of genuine profiles mistakenly flagged up as fake -- of around one per cent. "Online dating fraud is a very common, often unreported crime that causes huge distress and embarrassment for victims as well as financial loss," said Professor Tom Sorell of the University of Warwick.
"Using AI techniques to help reveal suspicious activity could be a game-changer that makes detection and prevention quicker, easier and more effective, ensuring that people can use dating sites with much more confidence in future," Sorell said. The aim is now to further enhance the technique and enable it to start being taken up by dating services within the next couple of years, helping them to prevent profiles being posted by scammers.
"The news that these AI capabilities have the potential to help thwart so-called 'rom-con' scams will be very welcome to the millions of people who use online dating services in the UK and worldwide," researchers said. In these scams, fraudsters target users of dating websites and apps, 'groom' them and then ask for gifts of money or loans which will never be returned. In 2017, over 3,000 Britons lost a total of 41 million pounds in such incidents, with an average loss of 11,500 pounds, researchers said.
(With inputs from agencies.)