Liveness test

A liveness test, liveness check or liveness detection is an automated means of checking whether a subject is a real person or part of a spoofing attack.

In a video liveness test, users are typically asked to look into a camera and to move, smile or blink, and features of their moving face may then be compared to that of a still image. Artificial intelligence is used to counter presentation attacks such as deepfakes or users wearing hyperrealistic masks, or video injection attacks.[1] The technique is used as part of know your customer checks in financial services[2] and during facial age estimation.[3]

Other forms of liveness test include checking for a pulse when using a fingerprint scanner[4] or checking that a person's voice is not a recording or artifically generated during speaker recognition.[5]

See also

• Artificial intelligence content detection
• Biometric spoofing
• Electronic authentication
• Identity verification service
• Multi-factor authentication
• Voice spoofing

Further reading

• "Biometric liveness follows growth trajectory of AI threats". Biometric Update. 2024-11-02. Retrieved 2025-01-22.

References

1. Simonchik, Konstantin (2024-05-02). "Video injection attacks: What is that and the way forward?". Biometric Update. Retrieved 2025-01-02.
2. Vincent, James (May 18, 2022). "Liveness tests used by banks to verify ID are "extremely vulnerable" to deepfake attacks". The Verge.
3. Omran, N; Alrayes, M; Khlifa, Z; Alfagi, A (July 2022). "Real-Time Liveness Detection Algorithm Based on Eyes Detection and Utilize Age Estimation Technique to Build a Controllable Environment" (PDF). International Science and Technology Journal. 30.
4. "How to prove and verify someone's identity". GOV.UK.
5. Slivova, Martina; Voznak, Miroslav; Tovarek, Jaromir; Partila, Pavol (March 1, 2022). "Detection of speaker liveness with CNN isolated word ASR for verification systems". Multimedia Tools Appl. 81 (7): 9445–9457. doi:10.1007/s11042-021-11150-1 – via ACM Digital Library.