NEW YORK, Jan 19, 2021 — ID R&D, the award-winning biometrics and liveness technology provider, announced that the latest release of its passive facial liveness, IDLive Face 1.18, features algorithms that reduce AI bias across demographic groups. Inclusive product development is a top priority for ID R&D and a major focus of this release is closing accuracy gaps between ages, genders, and ethnicities.
As IDLive Face continues to experience rapid adoption by customers and partners across a growing number of countries, tackling the issue of AI bias emerged as a leading initiative. Addressing this industry-wide challenge includes investing in unbiased data collection and classification. A new machine learning pipeline in IDLive Face 1.18 further enables this initiative with improved model training for higher accuracy.
The number of IDLive Face customers grew exponentially in 2020 and now the product conducts millions of passive liveness checks monthly, across 38 countries. This growth speaks directly to market demand for ID R&D’s next generation, single image passive liveness detection solution. The unique approach uses the same selfie image that is used for facial matching, which not only makes the process imperceptible to users, but also invisible to fraudsters.
As liveness detection becomes commonplace for identity verification, particularly in the financial sector, it is critical that products are built on inclusive data sets to prevent discrimination.
“IDLive Face is a breakthrough product in that it provides proven accuracy in even the most demanding, regulated financial environments with use cases such as onboarding,” said Alexey Khitrov, President at ID R&D. “However, unlike alternative liveness products we have had a relentless focus on enabling a zero-friction user experience. Improving speed and increasing accuracy, including both false accepts and false rejects, for all types of users and across various devices is critical to successfully using face for identity verification and authentication.”
IDLive Face is the only single image passive facial liveness detection product to achieve iBeta Level 2 Presentation Attack Detection compliance. Learn more about IDLive Face or contact us for a demo.