Paravision has achieved the lowest combined error rate among 15 vendors in the U.S. Department of Homeland Security’s recent evaluation of facial liveness detection technology. The company’s presentation attack detection (PAD) software demonstrated a combined error rate of just 3.6 percent in the Remote Identity Validation Technology Demonstration (RIVTD) Track 3 testing, significantly outperforming the second-best system which recorded an 8.5 percent error rate.
The testing evaluated both the accuracy and speed of passive liveness detection systems, which are crucial for preventing sophisticated presentation attacks in facial recognition applications. Paravision’s solution achieved a bona fide presentation classification error rate (BPCER) of 0.3 percent and an attack presentation classification error rate (APCER) of 3.3 percent, while maintaining processing speeds under one second per verification.
This performance milestone comes at a critical time, as synthetic identity fraud and injection attacks pose increasing threats to digital identity systems. The DHS Science and Technology Directorate (S&T) noted that Paravision’s system demonstrated consistent performance across demographic groups, addressing a common concern in biometric technologies.
“Paravision’s performance in the DHS RIVTD Track 3 proves that security and convenience are not mutually exclusive,” said Joey Pritikin, Chief Product Officer at Paravision. “With the latest approaches to Identity AI technology, new user experiences and security paradigms are made possible — offering rapid, reliable, and user-friendly fraud prevention.”
The company’s success builds on its previous achievements, including passing iBeta’s Level 2 assessment for ISO/IEC 30107 standard compliance. The technology has broad applications in identity verification workflows, particularly in scenarios where remote document processing and identity validation are essential.
The DHS evaluation results underscore the growing importance of reliable liveness detection in preventing identity fraud, as organizations increasingly rely on remote verification systems for secure access and authentication.
Source: Paravision
—
March 5, 2025 – by Ali Nassar-Smith
