Researchers Fool Airport Facial Recognition By Wearing Different Printed Masks
Researchers have proved airport facial recognition systems might not be as secure as we’d hope, as they managed to fool the cameras with different printed masks.
As technology becomes ever more advanced, we’ve started to rely on it for a number of things. Whether it’s to get us out of bed in the morning, remind us about appointments or simply to play our favourite songs, it’s now very much integrated into our lives.
Technology has been welcomed with open arms in airports as the use of machines has decreased waiting times when it comes to going through border control and boarding the plane, as facial recognition systems can quickly identify people and compare them to passport photos.
Recognising identity is essential for security, especially in airports, but it turns out the systems aren’t foolproof.
Earlier this week, researchers from artificial intelligence firm Kneron revealed they were able to deceive some facial recognition systems, and it didn’t take any intricate equipment to do so.
In fact, all it took was a printed mask.
The researchers used masks depicting another person’s face and tested systems across three continents. With the masks, they managed to successfully fool payment tablets run by the Chinese companies Alipay and WeChat, and a system at a border checkpoint in China, Business Insider reported.
They also managed to trick a facial recognition system at a passport-control gate at Schiphol Airport in Amsterdam.
Admittedly, the masks used were very realistic – I don’t think you’d be able to fool technology with a mask of the queen or President Trump picked up from your local costume shop, but it’s concerning to know that anyone who is able to get their hands on a more realistic mask could get away with pretending to be someone they’re not.
Kneron CEO Albert Liu commented on the findings in a statement, saying:
Technology providers should be held accountable if they do not safeguard users to the highest standards.
There are so many companies involved that it highlights an industry-wide issue with substandard facial recognition tech.
While the researchers were successful with a number of systems, they didn’t manage to fool Apple’s Face ID or Huawei’s system, which both use more sophisticated technology known as structured light imaging.
Kneron said its own facial recognition software also passed the test.
Those involved said the tests were carried out with the permission of security guards who were supervising the systems, and as there are usually people manning the machines hopefully anyone attempting to don a mask would be caught.
It’s clear humans still have a part to play when it comes to facial recognition!
If you have a story you want to tell, send it to UNILAD via [email protected]