printer friendly version

Securing ATMs 24/7

ATMs have become a cornerstone of day-to-day life for millions, but they can also be vulnerable to attack. The global ATM Industry Association reported an increase of ATM crime of 12% for 2017 ( www.securitysa.com/*atma1 – redirects to https://www.atmmarketplace.com/news/atm-deployers-report-double-digit-crime-surge-in-2017/). And attacks, of course, often involve ATM users, potentially injuring them and causing trauma. But since, by definition, ATMs are often situated outside buildings and used at all times of the day and night, securing them is a challenge – and banks are turning to more intelligent solutions.

An outdoor vulnerability

According to ATM Industry Association (ATMIA), there are an estimated 3.5 million ATMs in the world serving those in need of cash 24/7, 365 days a year. And that’s where the difficulty in securing them lies. To be effective, most ATMs need to be in public areas and open all hours. This, coupled with the fact that they hold cash, makes them an attractive target.

Criminals target these machines – or more precisely – the people using them, in numerous ways. Distracting customers at ATMs in an attempt to take cards or cash from them, or to discover their PIN number for use at a later date, for example. They also try to install false card readers that steal customers’ card details for reuse.

On the other side of the story, banks need to deal with customer disputes. A very small percentage of ATM transactions result in situations where the customer questions whether the transaction has been carried out as requested, or even disputes making the withdrawal at all.

So, security precautions for ATMs are an important part of a financial institution’s overall security solution. One such solution is highlighted below.

Deep Learning technology steps in

Inside an ATM machine, two covert cameras are installed, one trained on the user, the other on the ATM panel. Deep Learning technology embedded in the ATM security system can detect any ‘abnormalities’ in the facial scene in front of it, referring to existing data patterns. So, if there is another face in the picture (for example someone looking over a users shoulder), or if the person is wearing a mask, an alarm can be triggered in the security centre.

Using the same technology, the security system can also flag if the number pad is covered with a strip to steal PIN codes, or if a false card reader (or ‘skimmer’) is present to steal card details.

All of these ‘smart’ alarms streamline the security monitoring process, meaning that security personnel can react to real-time scenarios and not waste time on false alarms. The footage can provide evidence for any investigation.

The Deep Learning engine here would be the Hikvision DeepinMind NVR, which takes the information from the camera and analyses it. This can also manage footage, in conjunction with other NVRs and a video management system, which brings this part of a total solution together with all the other elements, providing a powerful toolset for security and business intelligence.

Securing assets at the extremities of your security solution is a lot easier with Deep Learning technology. Even ATMs outside your building can be safer, avoiding fraud and protecting your customers every day.

Share this article:

Further reading: