Innovatrics brings accuracy improvements to its liveness detection solution

In response to the user-friendly approach, passive liveness detection has gained popularity as it only requires the user to upload a selfie. The algorithm then analyzes this selfie to verify if it belongs to a real, live person.

Accuracy is of utmost importance in this technology. To further this advancement, Innovatrics has enhanced its passive liveness detection algorithms, resulting in a 30 percent increase in accuracy, the company says.

Innovatrics believes that malicious actors have recognized liveness detection as a potential vulnerability in biometric security systems. The company emphasizes the need for such solutions to remain updated to counter these evolving threats. Innovatrics’ passive liveness detection solution is measured by reducing the equal error rate (EER) from 1.3 percent to 0.9 percent.

The latest findings on Innovatrics’ passive liveness detection feature are divided into three primary categories: convenience, balanced, and security. Each category offers a different trade-off between the false acceptance rate (FAR) and false rejection rate (FRR).

The convenience category aims to minimize false rejections, even if it results in a slightly higher false acceptance rate. In the balanced category, the error rate reduction (ERR) metric of 0.9 percent (compared to its previous 1.3 percent) signifies a balanced point where both FAR and FRR are minimized. In the security category, the objective is to decrease the likelihood of false acceptances, even if it leads to a higher false rejection rate.

“We are seeing new avenues of attack almost every week and we have to make sure we’re able to detect them,” says Viktor Bielko, DOT (Digital Onboarding Toolkit) product manager at Innovatrics.

In recent news, the Digital Onboarding Toolkit (DOT) powered by Innovatrics’ ABIS (automated biometric identification system) has been integrated into Thailand’s digital infrastructure for unsupervised identity verification through a smartphone.

Article Topics

biometric liveness detection  |  biometric testing  |  biometrics  |  Innovatrics  |  passive facial liveness