Artificial fingerprints² have been developed by researchers who say they could one day be used to hack³ into everyday devices.

研究人员于日前开发出了人造指纹，并称其未来将可被用来解锁日常设备。

Researchers from New York University and Michigan State University successfully generated what they call "DeepMasterPrints".

纽约大学和密歇根州立大学的研究人员成功开发出了“深度学习指纹”。

These are machine-learning methods that act as a kind of "masterkey" which, the researchers claim, have the potential to unlock about one in three fingerprint¹-protected smartphones.

研究人员称，这种基于机器学习的算法相当于一把“万能钥匙”，有潜力解锁约1/3的受指纹保护的智能手机。

"Phones and many more devices don't capture your entire fingerprint," researchers told CNBC over the phone. "There's not enough space on the device, so they capture a partial fingerprint -- which is not as secure as the full image."

研究人员在接受消费者新闻与商业频道电话采访时表示：“手机和许多其它设备并没有捕捉到你的全部指纹信息。因为设备存储空间有限，它们只是捕捉了部分指纹，其安全性不如完整图像。”

Many developers were already making fingerprint scanners more secure by moving sensors⁴ from devices' buttons to screens, allowing them to pick up higher resolution images.

许多开发者已经开始通过将感应器从设备的按键转移到屏幕，让其采集到精度更高的图像，从而使指纹扫描的安全性更高。

"Some smartphones have the sensors on the side buttons, which are very thin -- they're convenient but less secure," the researchers said. "Their sensors only register a quarter or so of the fingerprint's features."

研究人员表示：“一些智能手机的侧边按钮上有非常薄的感应器，这虽然很方便，但不太安全。它们的感应器只记录了指纹特征的四分之一左右。”