FacePhi, CyberLink pass anti-spoofing face biometrics standard Level 2 compliance tests

FacePhi and CyberLink earned passing marks in evaluations to the biometric presentation attack detection (PAD) standard from the International Organization for Standardization (ISO) and International Electrotechnical Commission (IEC) to demonstrate that their face biometrics systems can detect fraud attacks known as spoofing. The trials were conducted by iBeta Quality Assurance in Colorado, which is certified by U.S. National Institute of Standards and Technology National Voluntary Laboratory Accreditation Program (NIST NVLAP).

FacePhi proves biometric fraud and identity theft protections

FacePhi received confirmation of its ISO/IEC 30107-3 Level 2 compliance to prove its facial recognition system’s protection against identity fraud and impersonation with more sophisticated attack methods.

The test consisted of FacePhi’s digital onboarding and authentication solutions being subjected to phishing attacks using animation software, latex and resin masks, and 3D photography.

“With this letter of compliance granted by iBeta, FacePhi demonstrates that its technology is strong and resistant to attacks, both level 1 and level 2 in accordance with ISO 30107-3”, says Jorge Félix, quality and systems director of FacePhi. Félix adds that, “in this way, the company continues to work on its commitment to the highest quality standards in the industry that recognize us as a safe product for our customers and users.”

The company passed Level 1 testing for ISO 30107 from iBeta in 2020, and more recently received certification for security and data protection needed to provide technology to Spanish public sector organizations.

CyberLink PAD system catches all 3D masks

Taiwan’s CyberLink announced its ‘FaceMe’ facial recognition system earned a nearly perfect score in iBeta’s PAD test, earning Level 2 compliance confirmation.

The Level 2 test is a more challenging gauntlet compared to level 1, which focuses on PAD from 2D photos and videos. Level 2 tests comprise of PAD from 3D masks that can come in the form of printed, resin, or latex. FaceMe achieved 100 percent spoofing prevention with 3D masks — an Attack Presentation Classification Error Rate (APCER) of 0 percent. For Bona Fide Presentation Classification Error Rate (BPCER), CyberLink missed 1.5 percent of PAD on iOS devices and 2.5 percent on Android devices. Effectively, FaceMe will detect 98.5 percent of biometric fraud attempts on Apple devices and 97.5 percent on Android devices.

In November 2021, CyberLink achieved APCER of 0 percent for Level 1 testing of FaceMe on iOS and Android.

“Biometric fraud prevention is one of the most critical imperatives for sectors of the economy such as fintech, where a security breach can take catastrophic proportions, but also wherever users are demanding remote access to sensitive data, fueling an explosive demand for remote authentication,” remarks Jau Huang, CEO of CyberLink. “The iBeta PAD test is widely recognized as the global standard for certifying the spoofing prevention performance of facial recognition technology offerings. Achieving Level 2 certification with a perfect score, anchors FaceMe as one of the very best facial recognition solutions to protect access from biometric fraud, even when presented with the most sophisticated attacks from 3D masks.”

Article Topics

biometric liveness detection  |  biometrics  |  CyberLink  |  face biometrics  |  FacePhi  |  fraud prevention  |  iBeta  |  ISO standards  |  ISO/IEC 30107-3  |  presentation attack detection  |  spoof detection