Apate, which is an artificial intelligence to trick phone scammers

Cyber ​​security experts have developed an artificial intelligence system to answer the calls of these scammers and waste their time by prolonging the chat for as long as possible.

While artificial intelligence (AI) is being used in phone scams, cyber security experts want to thwart scammers’ plans using the same technology. A team from Macquarie University, Australia, developed an artificial intelligence system that creates fake victims disguised as multilingual chatbots. The goal: to waste time for scammers to reduce the amount that victims lose every year because of them, i.e. 55 billion dollars.

Wasting time scammers

Called Apate – after the Greek goddess of deception – this system aims to rob scammers. The executive director of the university’s Cyber ​​Security Center, Dali Kavar, had the idea to develop it after receiving a fraudulent call while having lunch with his family. He managed to keep the prankster online for 40 minutes while his children laughed. “I realized that while I had wasted the crook’s time so he couldn’t get to the underdogs, and that was the point – it was also 40 minutes of my life from which I will never recover.”It is to explain.

Then Dale Wasteland began to think of a way to automate this process and“Using natural language processing to develop a computerized chatbot that can have a reasonable conversation with the fraudster”. The team began by analyzing fraud phone calls and identifying social engineering techniques that scammers use on their victims, using machine learning and natural language processing techniques.

Redirect fraudulent calls to chatbots

The chatbots were then trained on a dataset of real-world scam conversations (scam call recordings, scam email transcripts, etc.) so they could create their own conversations that were similar to those of the phone scams. “The conversational AI bots we developed can trick scammers into thinking they are talking to viable scam victims, so they spend time trying to fool the bots.”Daly Kaver said.

These chatbots are currently being tested on live fraud calls, redirecting calls from victims to a system developed by experts. The team put the numbers of these chatbots online, by entering them into spam applications or even by posting them on web pages, in order to increase the chances of receiving these fraudulent calls. Currently, chatbots are able to keep scammers online for an average of five minutes. The goal is for them to be able to do this for 40 minutes.

In an effort to spread this technology globally, the team is currently in discussions with several telecom service providers. “Partnership with telecom service providers will be key to making this really effective.”said the executive director of the university’s Cyber ​​Security Center.