Back to All Technologies

Liveness Detection

Liveness detection technology by Jumio increases the security of your biometric and facial recognition technology. An algorithm securely detects whether a biometric authentication sample is a live human being or a fake representation.

A Must-Have Feature for Biometric-Based Verification

Massive, broad-scale data breaches and the resulting rise of the dark web mean legacy identity verification and authentication methods have been compromised. Deepfakes, bots and advanced spoofing attacks assisted by rapidly evolving generative AI have made liveness detection a must-have feature in any biometric-based verification solution. Jumio integrates state-of-the-art liveness detection to thwart the well-documented vulnerabilities in less robust liveness technologies and biometric systems that are susceptible to spoofing.

Jumio steers clear of gesture-based gimmicks, like asking a user to blink, move their eyes or speak a random passcode, as these techniques add friction to the experience, and are also easily fooled by basic spoofing tactics. Jumio’s liveness detection simply requires the user to hold their mobile device at a natural angle. The solution then performs liveness and anti-spoofing detection using advanced selfie technology to ensure the user is real (not a photo, video or paper copy), is not wearing a mask and is physically present at the time of the detection. Active liveness detection algorithms use neural networks to help defend against fraudsters, identity theft and spoofing attempts to increase fraud prevention.

Get Started

Let a Jumio expert show you how easy it can be to integrate our automated identity proofing solutions into your existing processes.

Liveness Detection FAQs

1
Liveness detection uses machine learning and artificial intelligence technology to detect whether a person using a biometric verification method is a live person or a fake. Comparing biometric data provided during customer onboarding in real time will allow the algorithm to determine if a 3D mask, photo or video stream is being used.
2
High-quality facial liveness detection software will have no negative impact on the user experience. When performing a liveness check, the user interaction is fast and provides extra safeguards for the customer’s identity, improving the customer experience overall.
3
Passive liveness detection uses algorithms and deep learning to determine whether a user is a real person or a spoof without user interaction. While these are more complicated technologies, they often improve the user experience without sacrificing quality and efficiency. Active liveness detection requires the customer to perform a certain action that cannot be replicated through a spoof. This could be voice recognition, blinking eyes or making a certain hand gesture. Active liveness detection tends to be more time consuming than passive liveness detection.