The assessment by an accredited biometrics lab recognizes the importance of responsible AI and mitigating bias in liveness algorithms
NEW YORK, June 16, 2022 — ID R&D, a provider of top-performing facial liveness and voice biometrics products, today announced the results of the first independent evaluation of a liveness detection product for demographic bias. The assessment was performed by BixeLab, an accredited biometrics testing laboratory, and demonstrated that ID R&D’s IDLive® Face product for facial liveness detection exhibits fairness in terms of bias for target demographic groups including gender, age, and race.
Liveness detection is considered essential to preventing spoofing attacks where biometrics are used for digital identity verification and authentication. Similar to biometric matching algorithms, a biased liveness algorithm can lead to an increased rate of inaccurate results for individuals in a particular demographic group. This in turn can cause digital banking and other services to be less accessible for these customers.
The bias evaluation conducted by BixeLab fulfills several goals. It serves as recognition that bias in liveness detection presents the same potential as bias in biometric matching to impact people in specific demographic groups unfairly, and thus should undergo the same oversight and testing. Secondly, it helped establish methodologies for future evaluation of liveness detection. Thirdly, the test demonstrated that IDLive Face exhibits fair results across the target demographics. The outcomes of this report will inform ID R&D’s ongoing development of machine learning-based products in support of responsible AI. ID R&D products are used in over 70 countries globally.
“Spoof detection can introduce bias just as biometric matching algorithms can, but was being neglected as a bias contributor until now,” commented Alexey Khitrov, CEO and Co-founder of ID R&D. “We take biometric bias very seriously and hope this groundbreaking work contributes to efforts by others in our industry to address it.”
The BixeLab evaluation culminated in a comprehensive report, available upon request from ID R&D, that provides details about the testing methodologies applied and the results of the evaluation, as well as a confirmation letter that serves as a public attestation of the results. ID R&D has also published a white paper that discusses the topic of bias mitigation in liveness detection algorithms in depth, and offers best practices for using machine learning to develop products in support of responsible AI principles. ID R&D will also participate in a webinar hosted by Biometric Update to explore the subject on Thursday, June 30 at 9:30 am EDT.
About ID R&D
ID R&D, a Mitek company, is an award-winning provider of AI-based voice and face biometrics and liveness detection. With one of the strongest R&D teams in the industry, ID R&D consistently delivers innovative, best-in-class biometric capabilities that raise the bar in terms of usability and performance. Our proven products have achieved superior results in industry-leading challenges, third-party testing, and real-world deployments in more than 60 countries. ID R&D’s solutions are available for easy integration with mobile, web, messaging, and telephone channels, as well as in smart speakers, set-top boxes, and other IoT devices. ID R&D is based in New York, NY. Learn more at www.idrnd.ai.
Mitek (NASDAQ: MITK) is a global leader in mobile capture and digital identity verification built on the latest advancements in computer vision and artificial intelligence. Mitek’s identity verification solutions enable organizations to verify an individual’s identity during digital transactions to reduce risk and meet regulatory requirements, while increasing revenue from digital channels. More than 7,500 organizations use Mitek to enable trust and convenience for mobile check deposit, new account opening and more. Mitek is based in San Diego, Calif., with offices across the U.S. and Europe. Learn more at www.miteksystems.com.