Macquarie University cyber security experts have teamed up with Australia's largest bank to share scam intelligence to help prevent, detect and disrupt scams in a world-first pilot program that promises to undermine the business model of cybercriminals.
Apate.ai uses artificial intelligence (AI) to create voice clones that keep scammers on lengthy phone calls with AI chatbots.
The brainchild of Professor Dali Kaafar, Executive Director of Macquarie University's Cyber Security Hub, the anti-scam technology features realistic multilingual chatbots that can keep scammers on long fake calls and away from vulnerable people.
"Our model ties them up, wastes their time and reduces the number of successful scams," he says.
This proactive approach is a way to stay ahead of the scammers because they will have told you everything about the scam they are planning to deploy.
After receiving federal government funding to pilot the AI-powered anti-scam technology, Professor Kaafar's team is collaborating with CommBank to share scam intelligence to combat the multi-billion dollar losses suffered by victims of scam phone calls.
Apate is designed to disrupt scammers' business models - which relies on making a large profit from a small number of victims - and make it harder for them to reach potential victims.
Named after the Greek goddess of deception, Apate originally comprised about 100 bots designed to represent humans of various ages, gender and personalities who speak different languages.
Two years on, the anti-scam technology has advanced into a sophisticated army of chatbots that fools scammers into thinking they are talking to real people.
"We used to name each of them," Professor Kaafar says. "But now we have thousands of different bots emulating unique human behaviour."
Time wasting plus important intel
Not surprisingly, scammers rarely appreciate being fooled by Professor Kaafar's army of chatbots.
Professor Kaafar says he arrived at work one day to find his team celebrating their "very first f-word from a scammer" who was irate after learning he had spent more than half-an-hour talking to a chatbot.
Besides wasting scammers' time on calls, the AI-driven system extracts valuable intelligence about their tactics, the emotions they are trying to manipulate, the identity of impersonated organisations and new scam campaigns in real-time.
This information can be used by industry to warn their customers about cyber attacks and assist regulators such as the Australian Competition and Consumer Commission (ACCC) to catch fraudsters.
"While distracting scammers and engaging them with bots they think are genuine, you essentially have an opportunity to extract intelligence from the scammer's mouth," Professor Kaafar says.
"This proactive approach is a way to stay ahead of the scammers because they will have told you everything about the scam they are planning to deploy."
Scamming the scammers: Cyber security innovators Dr Michal Kepkowski, Dr Ian Wood, Dr Nardine Basta and Professor Dali Kaafar have developed new voice technology bots designed to stop scammers stealing money from people using phone scams.
Professor Kaafar says Apate has the capacity to distinguish genuine callers from scammers - information it can provide industry to improve their anti-scam technology.
The chatbots can also engage with text-based scammers on social media platforms such as WhatsApp and TikTok.
The development of AI-powered anti-scam chatbots comes amid a flood of phone scams globally enabled by technology that makes it easy and cheap for fraudsters to mask their location and pretend to call from any number.
Telecommunications providers block millions of scam calls every day, but it is difficult and expensive to upgrade communications infrastructure to improve authentication of calls and prevent scammers wreaking havoc on victims.
The ACCC reported phone calls were the number-one method used by scammers last year, with Australians losing $2.7 billion to cybercriminals.
The Global Anti-Scam Alliance estimates more than $1 trillion was lost by 2 billion scam victims last year, yet less than one per cent of scammers are caught.
Professor Kaafar says the amount of money stolen by scammers is almost certainly higher since most victims do not report the scam to police or government authorities.
Professor Kaafar says the successful deployment of Apate in the pilot project with CommBank will pave the way for a commercial launch of the technology.
"The idea is to engage with scammers on phone calls and all social media and extract as much intelligence as possible," he says. "The more we know, the better we can disrupt their operations and whole business models."
Professor Dali Kaafar is the Executive Director of Macquarie University's Cyber Security Hub in the Faculty of Science and Engineering, Macquarie University.
