SAFR SCAN, an AI-powered face authentication solution designed for mainstream commercial applications, has achieved a flawless 0 percent success rate against presentation attacks in independent testing conducted by iBeta, the industry standard for anti-spoofing testing.

iBeta Quality Assurance conducted Presentation Attack Detection (PAD) testing in accordance with ISO/IEC 30107-3. Accredited by NIST/NVLAP (NVLAP Testing Lab Code: 200962), iBeta provides rigorous evaluation of biometric systems against spoofing attempts. A presentation attack occurs when an unauthorized individual attempts to gain access by presenting fake biometric data, such as photos, videos, or 3D masks, to a facial recognition system. SAFR SCAN yielded an overall Presentation Attack (PA) success rate of 0 percent, as well as an Imposter Attack Presentation Accept Rate (IAPAR) of 0 percent and a bona fide False Non-Match Rate (FNMR) of 0 percent.

“Presentation attacks are the single biggest security threat to face-based access control devices,” said Brad Donaldson, vice president of computer vsion, SAFR from RealNetworks. “Detecting sophisticated attempts to spoof these devices using both 3D and 2D liveness technologies is what differentiates SAFR SCAN from other devices.”