To obtain access to full text of journal and articles you must register!
- Article name
- Protection against deepfake attacks on facial recognition systems. Eye movements liveness detection
- Authors
- Batmaev V. B., , vbbatmaev@gmail.com, Moscow Institute of Physics and Technology (National Research University); SC "OKB SAPR", Moscow Region, Dolgoprudny, Russia; Moscow, Russia
Novikov Yu. A., , ynov716@gmail.com, SC "OKB SAPR", Moscow, Russia
- Keywords
- biometrics / liveness detection / deepfake / replay attack / eye movements
- Year
- 2025 Issue 4 Pages 35 - 39
- Code EDN
- KKHYOW
- Code DOI
- 10.52190/2073-2600_2025_4_35
- Abstract
- This article presents an interactive liveness detection method for remote biometric authentication systems that analyzes eye movement trajectories as users track a random visual stimulus. We propose an algorithm that matches the user's gaze trajectory to the stimulus trajectory by adjusting temporal shifts and analyzing statistical features. We conducted an experimental study using 122 recordings. Our method achieved an Equal Error Rate (EER) of 1.6 %, matching the current state-of-the-art in liveness detection. The results demonstrate that this approach effectively protects against replay attacks using standard mobile device capabilities.
- Text
- BUY for read the full text of article
- Buy
- 500.00 rub
