研究人員于日前開發(fā)出了人造指紋,并稱其未來將可被用來解鎖日常設備。
Researchers from New York University and MichiganState University successfully generated what theycall "DeepMasterPrints".
紐約大學和密歇根州立大學的研究人員成功開發(fā)出了“深度學習指紋”。
These are machine-learning methods that act as akind of "masterkey" which, the researchers claim, have the potential to unlock about one inthree fingerprint-protected smartphones.
研究人員稱,這種基于機器學習的算法相當于一把“萬能鑰匙”,有潛力解鎖約1/3的受指紋保護的智能手機。
"Phones and many more devices don't capture your entire fingerprint," researchers toldCNBC over the phone. "There's not enough space on the device, so they capture a partialfingerprint -- which is not as secure as the full image."
研究人員在接受消費者新聞與商業(yè)頻道電話采訪時表示:“手機和許多其它設備并沒有捕捉到你的全部指紋信息。因為設備存儲空間有限,它們只是捕捉了部分指紋,其安全性不如完整圖像。”
Many developers were already making fingerprint scanners more secure by moving sensorsfrom devices' buttons to screens, allowing them to pick up higher resolution images.
許多開發(fā)者已經(jīng)開始通過將感應器從設備的按鍵轉移到屏幕,讓其采集到精度更高的圖像,從而使指紋掃描的安全性更高。
"Some smartphones have the sensors on the side buttons, which are very thin -- they'reconvenient but less secure," the researchers said. "Their sensors only register a quarter orso of the fingerprint's features."
研究人員表示:“一些智能手機的側邊按鈕上有非常薄的感應器,這雖然很方便,但不太安全。它們的感應器只記錄了指紋特征的四分之一左右。”