Can AI Help Protect Us From Online Dating Scams?

Online dating apps are an increasingly common way for people to meet partners, but just as algorithms have become adept at matching us with suitable people, so to have fraudsters become adept at creating fake profiles to try and con people out of money.

Recent work from the University of Warwick aims to use artificial intelligence technology to fight back. Their technology is designed to understand in detail what fake profiles look like so they can constantly scan dating sites for fraudsters and warn innocent users of their presence. They will analyze everything from the demographic information and images of the profile, to the descriptions provided for that person.

When the system was tested, it proved remarkably effective, with a very low false-positive rate of 1 percent recorded. The team is not content with this, however, and aims to continue developing it so that it is market ready.

The Rise of Dating Scams

Dating scams have unfortunately been becoming more prevalent in recent years, with criminals using dating websites to target individuals and solicit gifts or money from them. In 2017, it's estimated that over 3,000 people in the UK were hit by such a scam, with over £41 million lost as a result.

The project team included a wide range of partners, including researchers from King's College London, Cardiff University and the University of Bristol. In addition to exploring the technical nature of fake online profiles, the team also explored the psychology of dating scams to test whether particular people tend to be most vulnerable.

"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," the team explains.