ID R&D Passive Facial Liveness First to Achieve iBeta Level 2 with Single Frame Approach

IDLive Face is the only single image, passive biometric liveness solution to pass iBeta Level 2

ISO 30107-3 Level 2 BadgeNEW YORK, October 12, 2020 — ID R&D, the award-winning biometrics technology provider offering AI-based voice, face, and behavioral biometrics and voice and face anti-spoofing products, today announces its unique facial liveness detection solution, IDLive™ Face, has been awarded iBeta Level 2 Presentation Attack Detection Compliance in accordance with ISO/IEC 30107-3. IDLive Face had a perfect score on the Presentation Attack Detection (PAD) conformance testing with zero attacks getting through and is the world’s first product to do so using a passive, single frame approach. The product previously passed Level 1 Compliance testing, also with a perfect score.

ID R&D released IDLive Face in 2019 to fight fraud during authentication and digital onboarding without introducing friction. The result is stronger security, a better user experience, and reduced abandonment. The product is now in production with more than 25 biometric systems integrators, eKYC solution providers, and enterprise customers around the world.

Unlike other solutions that require users perform actions or gestures to distinguish a live person from a photo, video or mask, IDLive Face is entirely passive for a fast and simplified user experience. The product is unique in that it does not rely on multiple images or video to determine liveness, but rather a single image. In fact, it relies on the same selfie used for face recognition. This results in specific advantages, including:

  • Requires no additional software on the capture side.
  • Works for both iOS and Android devices
  • Generates no incremental traffic to the server, making it ideal for customers operating in countries where bandwidth is scarce or expensive. A single image can be as small as 50kb when using ID R&D recommended settings versus solutions that send multiple frames or video of photos.
  • Eliminates the vulnerability that occurs when liveness detection is separate from the action to capture the selfie for face recognition
  • Determines liveness in under a second.
  • Enables easy integration because the product is deployed as a separate independent function, requiring no changes to the user interface or communication interfaces.

ID R&D algorithms work on images that meet minimum requirements typical of a “selfie,” and as such, the product supports the majority of smartphones or web cameras. The API is simple, consisting of only a single image as input and a probability of liveness result as an output.

“Passing iBeta Level 1 and 2 PAD compliance testing with a fully passive, single frame product is a true milestone in enabling strong, frictionless identity verification. Other companies take different approaches, not because they want to make the user experience harder, but because detecting liveness without extra movements and images or video is a huge challenge,” said Konstantin Simonchik, ID R&D Chief Science Officer. “Not only is this a tremendous achievement for the team, but a demonstration of significant technological progress — further proving that Artificial Intelligence can surpass human vision and that Human Intelligence can surpass any AI issue.”

iBeta is the industry leader in biometrics testing and a globally-acclaimed quality assurance provider offering industry certification and software testing for companies around the globe. iBeta is the only accredited biometrics testing lab by the National Institute of Standards and Technology (NIST) under the National Voluntary Laboratory Accreditation Program (NVLAP). With a Quality Management System and biometrics test procedures independently audited by NVLAP in a comprehensive technical evaluation, iBeta Quality Assurance conducts independent biometric testing for wearable and mobile and other devices using the modalities of facial recognition, palm recognition, voice recognition, and fingerprint recognition.

During the evaluation, iBeta researchers conducted 1500 total presentation attacks across two mid-level smartphones (Samsung Galaxy S8 Plus and iPhone 6S Plus). None of these presentation attacks were successful. ID R&D earned an Attack Presentation Classification Error Rate (APCER) of 0% and passed Level 2 compliance testing.

To learn more about ID R&D single frame passive liveness, read our recent tech brief.

About ID R&D

ID R&D is an award-winning provider of multimodal biometric security solutions. Based in New York, NY, ID R&D combines science-driven technological capabilities with leading research and development to deliver seamless authentication experiences. ID R&D’s solutions are available for easy integration with mobile, web, and IoT applications, as well as in smart speakers, set-top boxes, and other IoT devices. Learn more about ID R&D’s voice and face biometrics, voice and face biometric anti-spoofing, multimodal biometrics, and audio event detection at https://www.idrnd.ai

Menu