Tackling Deepfake Scam Calls With Syntelligence AI

AI deepfakes has been spreading like wildfire on social media platforms – and their might is not limited to visual content.

Deepfaked voices – created through the manipulation of real voices – is an increasing concern, with one in four American consumers having received deepfake voice calls in 12 months.

This is according to a new survey of approximately 12,000 consumers by Hiya across the US, UK, Canada, France, Germany and Spain.

Abruptly receiving these calls can sometimes be panic-inducing and, with the receiver feeling pressured to act quickly, the financial loss can be significant.

Globally, telco fraud losses reached US$41.82bn, according to the Communications Fraud Control Association (CFCA) Fraud Loss Survey Report.

Syntelligence AI – founded by Deutsche Telekom, e&, Singtel Group, SK Telecom and SoftBank – is using AI training datasets made by the five telcos to combat some of the biggest cyber frauds facing voice communication networks.

Network-level threat detection

These threats are targeted at network level with Syntelligence AI – rather than on individual devices. This starts with the 'Trust Platform', which addresses issues such as declining user trust in calls from unknown numbers and the effective screening of spam callers.

Its Security Shield platform offers a real-time defence model which detects and blocks scam calls before they reach people.

"The telecommunications industry is entering a new phase in user experience and operational efficiency, enabled by rapid advances in AI," says Prateek Choudhary, CEO of Syntelligence AI.

"It's a significant moment which offers telecom companies a real opportunity to shape what comes next. Building AI-powered services that strengthen their role will deepen customer value and set a new standard for network experience for years to come."

AI-powered defence strategy

At MWC Barcelona, Deutsche Telekom's Vice President Jan Hofmann and Syntelligence AI's CEO delivered a panel discussing how the Global Telco AI Alliance is rewriting the rules of network trust.

Prateek said: "We think that AI is the best way to actually solve the problem which is being made worse by AI.

"What we are doing here is creating a platform called the Trust Platform, which protects you from the first time the phone rings until the end of the call, the entire lifecycle of the call."

Prateek explains the four stages that the Trust Platform uses through AI assistance: "Before the phone rings, the networks have a lot of information, we are leveraging that to determine whether or not the call is a scam or not – so what we call the scam risk assessment."

He further elaborates that telecoms use network signals to do this, including roaming status, traffic patterns (e.g. the number of people the phone number has called in the last 24 hours) and crowd intelligence.

"The second, when the call is ringing from an unknown number, a person can decide to send that call to an AI assistant. This is basically understanding the intent, understanding why a person is calling. It gathers all the information, summarises it, and lets the person know whether the call was a scam or not.

"If people do decide to take the call themselves, we monitor the call and see if it is evolving in to the scam call and we give the right alerts to make people aware that the call could be a scam. Then we take the feedback."

Proactive intelligence approach

"By training proprietary AI models on telco-scale data, we are identifying intent before the phone even rings," Syntelligence AI states in a LinkedIn post. 

"We're moving from reactive filters to proactive intelligence."

This proactive approach represents a fundamental shift in how telecommunications networks handle security threats. Rather than waiting for scam patterns to emerge and then responding, the AI models analyse network-level data in real time to predict and prevent fraudulent calls before they connect.

This intelligence-driven methodology leverages the collective data from multiple global telcos, creating a more robust defence system that learns and adapts continuously.

As the AI call assistant solution is rolled out across telco networks, including the five which founded Syntelligence AI, networks could become more secure and less prone to voice call scams.

The volume of AI deepfake voice call scams have risen at a compound annual rate of 16% since January 2023, according to Hiya's survey.

With scams leading to financial fraud or identity theft of all individuals, not just telcos, Syntelligence AI's technology has the potential to become a global solution for defending against voice-based cyber threats.