Color wave: A systematic evaluation of active screen illumination for injection attack detection in remote face authentication

Authors: Daniyar Kurmankhojayev, Elmurat Nigmatov, Dmitrii Gordin, Andrei Shadrikov, Mikhail Shkorin, Danijar Gabdullin, Vyacheslav Shen

Published: 2026-11-09 08:44:26+00:00

AI Summary

This research systematically evaluates "color wave," an active screen illumination method for detecting injection attacks in remote face authentication. The approach introduces randomized visual stimuli via the device screen and analyzes facial responses. The study classifies injected content into static images, prerecorded videos, and real-time deepfakes, developing a specific evaluation protocol to assess detection effectiveness, generalization, robustness, and susceptibility to evasion strategies.

Abstract

Remote face authentication requires protection against both presentation attacks and biometric data injection attacks prior to face matching. Methods based on active screen illumination appear promising for both by introducing randomized visual stimuli through the user's device screen and evaluating the corresponding facial responses. Although such methods have been more studied for presentation attack detection (PAD), their systematic evaluation for injection attack detection (IAD) remains limited. To address this gap, we first classify injected content into static images, prerecorded videos, and real-time deepfakes based on their expected responses to the challenge. We then adapt an active screen-illumination approach into an implementation we term color wave and develop a systematic, injection-specific evaluation protocol. The protocol examines detection effectiveness, generalization across operating conditions, robustness to signal degradation, and susceptibility to selected evasion strategies. The findings demonstrate a strong discriminative signal under controlled conditions but also reveal performance limitations under overexposure, low screen brightness, and subject motion, as well as vulnerabilities to selected evasion strategies. By relating detection outcomes to attack types and operating conditions, this study provides an interpretable assessment of when and why active screen illumination succeeds or fails as an IAD mechanism.


Key findings
The method shows strong discrimination against static images, prerecorded videos, and real-time deepfakes under controlled conditions, achieving 100% accuracy in baseline validation. However, performance degrades with overexposure, low screen brightness, subject motion, and dropped frames. It also demonstrates vulnerability to sufficiently responsive automatic stimulus-conditioned video manipulation, suggesting it should be part of a layered security system.
Approach
The "color wave" method generates a randomized sequence of color stimuli on the user's screen. The camera captures the facial video, which is analyzed for temporal delays, predicted facial-response colors, and response-duration matching. A session is classified as bona fide only if all three criteria (delay, color agreement, duration matching) meet empirically determined thresholds.
Datasets
Calibration dataset (90 bona fide sessions) and an Evaluation dataset (1128 sessions: 666 bona fide, 462 attack).
Model(s)
A CNN-based classifier is used as the response-color predictor to learn spatially varying color-response features from neutral and illuminated facial observations.
Author countries
Kazakhstan