All it takes to fool facial recognition at airports and banks is a printed mask, researchers found
- Researchers were able to fool facial recognition software at airports and banks using a printed mask, highlighting security vulnerabilities.
- The tests were carried out across three continents, fooling mobile payment tablets, a Chinese border control station, and a passport control gate at Amsterdam's Schiphol airport.
- However, researchers were unable to fool some facial recognition software, including Apple's Face ID.
- Visit Business Insider's homepage for more stories.
Facial recognition is being widely embraced as a security tool - law enforcement and corporations alike are rolling it out to keep tabs on who's accessing airports, stores, and smartphone lock screens.
As it turns out, the technology is fallible. Researchers with the AI firm Kneron were able to fool facial recognition systems at banks, border crossing checkpoints, and airports using a printed mask depicting a different person's face, they announced Thursday.
Researchers tested facial recognition across three continents. They successfully fooled payment tablets run by Chinese companies Alipay and WeChat, as well as a border crossing checkpoint in China. In Amsterdam, the printed mask fooled a facial recognition checkpoint at Schiphol airport.
The researchers say their findings suggest that anyone who prints out a lifelike mask resembling someone else can bypass security checkpoints to fly or shop on their behalf.
"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," Kneron CEO Albert Liu said in a statement.
Some facial recognition software proved impervious to the printed mask test, however. Researchers wrote that Apple's Face ID and Huawei's facial recognition both passed their test - both of which use more sophisticated technology known as structured light.
Researchers noted that, for the most part, the tests were carried out with the permission of human security guards supervising the checkpoints - as long as humans are present and notice the mask, facial recognition checkpoints aren't entirely unsecure.
