News
The operator says its AI-powered spam detection solution is catching over 100 million potential spam calls a day
This week, Bharti Airtel has announced the rollout of its new AI-powered spam detection solution.
The solution, which has reportedly been developed over the past year, is able to analyse calls and alert the receiver of a potential spam call in just 2 milliseconds. The caller then has the option of whether to block the call or not.
The solution uses a purpose-built algorithm to accurately classify communications as “Suspected SPAM”, as well as scanning SMS messages for malicious links that have been identified on a centralised database.
“In 2 milliseconds our solution processes 1.5 billion messages and 2.5 billion calls every day. Our solution has been able to identify 100 million potential spam calls and 3 million spam SMSes originating every day,” explained Airtel CEO Gopal Vittal.
The solution will be rolled out to all of Airtel’s 387 million Indian customers for free.
“Spam has become a menace for customers. We have spent the last 12 months to solve this comprehensively. Today marks a milestone as we launch the country’s first AI-powered spam-free network that will shield our customers from the continuous onslaught of intrusive and unwanted communications,” said Vittal.
Calls and messages made through apps, such as WhatsApp, will be unaffected, a fact that Vittal called “one of the pain points” in the ongoing battle against spam.
The scale of the spam calling challenge in India is enormous. Earlier this year, media reports suggested that more than 60% of Indian’s receive three or more spam calls a day.
Indeed, the issue is well known by the government, which set up the National Do Not Call Registry (NDNC) in response in 2011; this allows registered mobile users to opt out of unwanted marketing calls.
While the NDNC has reduced the number of spam calls to these customers, data suggests it is far from perfect, with a survey from LocalCircles showing that 95% of people who registered still receive unwanted calls and messages.
Ironically, while AI is here being used to combat spam, it should be noted that it is also being used by bad actors to help facilitate it. Last year, for example, the US Federal Communications Commission (FCC) announced that it would be assessing AI’s impact on robocalling and telefraud, noting that AI deepfakes were becoming increasingly adept at mimicking users voices.
“While we are aware of the challenges AI can present, there is also significant potential to use this technology to benefit communications networks and their customers—including in the fight against junk robocalls and robotexts,” said FCC chairwoman Jessica Rosenworcel. “We need to address these opportunities and risks thoughtfully, and the effort we are launching today will help us gain more insight on both fronts.”
Keep up to date with all of the latest telecoms news with Total Telecom’s daily newsletter
Also in the news:
Meta resumes use of UK user posts to train its AI models
Verizon’s 4,800 job cuts will cost over $1.9 billion
CMA questions Vodafone–Three merger after second probe