Passive Liveness Check Is More Secure & Seamless Compared to Active Check, Data Shows

When onboarding new clients remotely, biometric verification is just one of the steps organizations need to take. It’s equally important to make sure that the client is indeed present and not trying to spoof the system with a presentation attack.

Early PAD “Active Liveness” technologies focused on instructing users to carry out voluntary reactions to prompts, such as tilting their head a certain way or following a randomly moving object with their eyes (This was the method used in the early iterations of Innovatrics Digital Onboarding Toolkit). These methods, while effective to a point, can be outsmarted with a little effort and ingenuity.

More recently, technology vendors have come up with more advanced methods of detecting presentation attacks. These new methods fall under the category of “Passive Liveness”, as they do not require the user to carry out any actions in order to allow the algorithm to calculate their liveness score. This is where things start to get interesting.

Passive liveness uses image recognition deep learning techniques to tell a real face from an image. The training set contains many different spoof vectors: printed photographs, printed masks, 3D masks, and screenshots from a mobile or PC screen.

The Data Shows the Winner

So which approach is better in real world applications such as remote onboarding? The evidence we’ve gathered from dozens of deployments is conclusive. One of our early-adopter customers initiated their project using Active Liveness, then took the decision to upgrade to Passive Liveness in 2020. The result?

• Active Liveness: 63% of customers successfully completed this step, taking an average of 13 seconds
• Passive Liveness: 99.9% of customers successfully completed this step, taking an average of 1 second

By introducing Passive Liveness, we simultaneously improved the user onboarding experience and increased the overall security of the application.

What’s more, when we ran the Passive Liveness detection algorithm over their existing database (of over 30 million onboarding images), we found out that approximately 1% of all previous onboardings had been completed with the help of a presentation attack. Armed with this information, our customer was able to close down these accounts, protecting their business from potential fraud.

Interested in our Digital Onboarding Toolkit? Contact us or try our demo.