Aware Ranks Top Performer in NIST Face Analysis Technology Evaluation (FATE) Benchmarking Test While Optimizing Demographic Parity

Aware’s facial presentation attack detection (PAD) algorithms achieved top ranking among 82 tested systems in the newly introduced NIST Face Analysis Technology Evaluation (FATE) test - NIST IR 8491.


BURLINGTON, Mass., Oct. 11, 2023 (GLOBE NEWSWIRE) -- Aware, Inc. (NASDAQ: AWRE) continues to build on its 30-year history of innovation, broad IP and biometric leadership and its commitment to deliver customers the highest level of technology with accurate, non-biased, fast algorithms, as evidenced by its performance in the National Institute for Standards and Technology’s (NIST) independent Face Analysis Technology Evaluation (FATE). The independent NIST results show Aware as a leader in presentation attack detection liveness technology while affirming Aware’s leadership position in optimizing demographic parity.

According to NIST, the FATE “evaluated the ability of software-based algorithms (software only, no hardware dependance) to detect the presence of presentation attacks in conventional 2D still and video imagery of human faces. The report surveyed the trade-off between false alarm rates on legitimate non-attack images and detection rates on images of various presentation attack instruments (PAIs).” Consistent with NIST’s Face Recognition Vendor Test (FRVT), the test results of NIST FATE are likely to become the trusted standard globally. This will bring a much-needed standard in benchmarking based on ISO 30107 (which is also called “anti-spoofing” or “liveness detection” for the solutions aimed at solving the presentation attack detection (PAD) problem).

As stated in the report: “The test results quantified the accuracy of passive, software-based face PAD algorithms applied to imagery of different PAIs… FATE PAD had two separate tasks that evaluated algorithms with an ability to detect 1) impersonation attacks and 2) evasion attacks... All algorithms [82] implemented the impersonation detection task, and 27 of those algorithms also implemented the evasion detection task... [The] evaluation dataset contained imagery (primarily stills) of approximately 20,000 presentation attack attempts and 21,000 bona fide presentations, which included 9 categories of presentation attacks.”

Aware achieved the rank #1 in security for both impersonation and evasion detection for the TYPE 4 PA.

NIST did not disclose all the PAIs used in the evaluation to encourage broad PAD effectiveness and to discourage tuning to specific attacks. NIST explained the rationale behind the choice to not disclose the evaluation method because it “reflects the operational reality that attackers do not advertise their methods.” Detection metrics for each PAI are reported but most are without description of the PAI. “PAs used to evaluate impersonation detection were also used to test evasion detection (by definition, impersonation is also a form of evasion).”

While accuracy and convenience are both important to a PAD solution, they are not sufficient. Speed and fairness are equally critical and Aware performed exceptionally well. Eliminating racial, gender, and other biases to achieve optimal demographic parity has been Aware’s focus for years in both face recognition and presentation attack detection. The results show that Aware continues to lead in this area.

“Aware applauds NIST for both the rigor and the thought leadership demonstrated in designing this evaluation,” says Dr. Mohamed Lazzouni, Chief Technology Officer at Aware. “Aware strongly believes in building systems in tune with the operational conditions we encounter in our daily lives. As such, providing an optimal experience to balance security and convenience is critical. This is why Aware participated in both impersonation and evasion tasks and performed exceptionally well in both.”

Aware continues to demonstrate that the use of deep learning and sophisticated fusion strategies are critical building blocks for biometric artificial intelligence (AI) systems to advance current algorithms and build next generation ones. Aware’s core algorithms, as well as the systems built on them, use facial recognition and presentation attack detection deployed around the world. Aware has leveraged the operational scenarios to teach the AI-based algorithms to continue to improve performance and adapt to emerging threats. Aware does so without compromising customer experience or fairness.

“Aware’s performance would not have been possible without the continuous support of our customers,” continues Lazzouni. “They’ve provided invaluable feedback throughout the years and assisted us in making Aware one of the leading PAD systems on the market. We will continue to demonstrate that the use of deep learning and sophisticated fusion strategies are critical building blocks for biometric AI systems to advance current algorithms and build next generation ones.”

Aware continues to build on its commitment to delivering to customers the highest level of technology with accurate, non-biased, and fast algorithms packaged in full systems that are easily configurable to balance between low friction and high security, can be easily integrated using flexible deployment models, and have fast ramp-up times with low-code/no-code platforms.

For more information regarding the NIST FATE report and results, or to learn more about Aware’s presentation attack detection systems, contact Aware today.

About Aware
Aware is a global authentication company that validates and secures identities using leading-edge adaptive biometrics. Aware’s offerings address the growing challenges that government and commercial enterprises face in knowing, authenticating and securing individuals through frictionless and highly secure user experiences. Now celebrating the company’s 30th anniversary as a leader in biometrics, Aware’s algorithms are based on diverse data sets from around the world and can be tailored to the unique security needs of its customers. The company empowers users to have control over identities through clear, easy opt-in and opt-out features, helping them feel secure and improving their lives. Aware is a publicly held company (NASDAQ: AWRE) based in Burlington, Massachusetts. To learn more, visit https://www.aware.com or follow Aware on Twitter @AwareBiometrics.

 

Mot-clé


Coordonnées