AI may help pinpoint and foil online dating scams

Dating websites and apps could be using computing algorithms soon to help pinpoint online dating scams. In other words, dating apps and websites may soon use artificial intelligence to protect members from fraudsters. The AI pinpoints fake profiles which have helped criminals con victims out of huge sums of money.

Researchers from the University of Warwick in England have developed algorithms that ‘think’ like humans. Their work is part of wide-ranging research into combating online fraud.

The computer scientists have designed the new algorithms specifically to understand what fake dating profiles look like. They then apply this knowledge when scanning profiles on dating websites and apps.

The artificial intelligence automatically seeks out suspicious signs that fraudsters have included inadvertently. These signs may be in the demographic information, self-descriptions, and images that make up the fraudsters’ profiles.

Put simply; the algorithms determine whether each profile is authentic or fake.

Tests showed that the algorithms produced an extremely low false-positive rate of about 1%. A false-positive is a genuine profile that the AI flagged up as fake.

---

Installing the algorithms in online dating websites

The researchers now want to improve the technique further. Over the next two years, they plan to place their algorithms in real online dating services. They believe that their technology will help dating sites and apps prevent scammers from posting fake profiles.

According to a press release by the Engineering and Physical Sciences Research Council, which part-funded the study:

“With Valentine’s Day fast approaching, the news that these Artificial Intelligence (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.”

“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 in such incidents, with an average loss of £11,500.”

Examining online dating messages and profiles

Prof. Awais Rashid, from the University of Lancaster, and Dr. Gianluca Stringhini, from Boston University, led the work on the textual and other computer characteristics of online dating profiles and messages.

Their work formed part of the overall research initiative in which Cardiff University, King’s College London, and partners worldwide also collaborated.

The initiative aims to prevent mass fraud that exploits websites and apps. The initiative has also focused on gaining a better understanding of the psychology of individuals most likely to become repeat victims. Specifically, repeat victims of online scams.

Initially, Prof. Monica Whitty, from the University of Melbourne, led the project. Then, Prof. Tom Sorrell, from the University of Warwick, took over in the final stages.

Prof. Sorell said:

“Online dating fraud is a very common, often unreported crime that causes huge distress and embarrassment for victims as well as financial loss.”

“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.”

---