Oz Forensics passes Level 3 biometric PAD evaluation by BixeLab with no errors

Oz Forensics has passed a Level 3 evaluation of its face biometric Presentation Attack Detection (PAD) technology based on the ISO/IEC 30107-3 by BixeLab with no errors reported.

BixeLab tested the OzLiveness Web SDK with mobile devices running Android 16 and iOS 26, with four species of Level C Presentation Attack Instruments (PAIs) specifically designed to spoof 5 consenting subjects. The test results are based on 100 Level C presentation attacks and 50 bona fide transactions carried out by 10 subjects, the confirmation letter from BixeLab states.

In those attempts, Oz’ PAD technology committed 0 errors, for an Attack Presentation Classification Error Rate (APCER) and a Bona Fide Presentation Classification Error Rate (BPCER) each of 0 percent.

Oz completed ISO 30107 conformance testing with BixeLab for Levels 1 and 2 midway through 2025, refreshing previous assessments, and then completed a biometric Injection Attack Detection (IAD) assessment by BixeLab last September.

BixeLab explained the significance of Level 3 PAD evaluations, which test the software’s ability to correctly identify attacks carried out with a high degree of effort, skill and resources, in a paper posted to its website in February.

Building trust in liveness detection is also one of the central aims of the continuously-updated Trust Center Oz launched just weeks ago.

Face deepfake detection is forecast to generate $2.52 billion in revenue by 2027, according to the 2025 Deepfake Detection Market Report & Buyer’s Guide from Biometric Update and Goode Intelligence. The report includes a case study featuring Oz Forensics and a profile of the company.

Article Topics

biometric liveness detection  |  biometrics  |  BixeLab  |  face biometrics  |  ISO/IEC 30107-3  |  Level 3 PAD testing  |  Oz Forensics  |  presentation attack detection