A Dual-Stream Challenge-Response Protocol for Ocular Liveness Verification

View on arXiv ← Back to list

Authors: Ismail Kably

Published: 2026-07-10 18:15:23+00:00

Comment: 6 pages, 2 figures. Simulation-based theoretical framework; human-subject validation identified as future work

AI Summary

This paper introduces a Spatio-Luminance Sensor Fusion protocol, a dual-stream challenge-response framework for ocular liveness verification. It combines gaze tracking and pupillary light reflex metrics into a simultaneous authentication challenge using randomized, time-varying visual stimuli. Through Monte Carlo simulation, the protocol demonstrates theoretical separability between genuine and simulated attack conditions, especially against generative deepfakes with rendering latency.

Abstract

Ocular biometric systems face sophisticated presentation attacks, including high-resolution video replays and real-time generative deepfakes, which easily bypass static liveness checks. Current Presentation Attack Detection (PAD) frameworks typically rely on isolated physiological metrics, such as gaze tracking or the Pupillary Light Reflex (PLR), which can be spoofed independently. This paper proposes a Spatio-Luminance Sensor Fusion protocol, which introduces a dual-stream challenge-response framework for ocular liveness verification by uniting these metrics into a simultaneous authentication challenge. By generating a randomized, time-varying visual stimulus that fluctuates in both spatial trajectory and luminance intensity, we construct a mathematically coupled state-space likelihood model, termed the Synchronization Matrix, to evaluate the continuous cross-correlation between the expected biological latencies of smooth pursuit tracking and pupillary constriction. Using Monte Carlo simulation grounded in literature-derived latency distributions, we demonstrate theoretical separability between genuine and simulated attack conditions, and show that a multi-round challenge design improves the detection of generative deepfakes when a non-zero rendering-latency gap exists. This work provides a simulation-supported theoretical framework for next-generation dynamic spoofing defense in ocular and iris biometrics; human-subject validation is identified as necessary future work before deployment claims can be made.

Key findings
The proposed protocol shows strong theoretical separability between genuine responses and presentation attacks like video replays and mechanical spoofing (AUC up to 1.000). Deepfake detection is highly dependent on rendering latency, with detectability significantly improving (AUC rising to >=0.997) for latencies beyond 75ms. A multi-round challenge design further improves deepfake detection when a non-zero rendering-latency gap exists.
Approach
The approach generates a randomized, time-varying visual stimulus that fluctuates in both spatial trajectory and luminance intensity. It then constructs a 'Synchronization Matrix' (Sjoint) to evaluate the continuous cross-correlation between expected biological latencies of smooth pursuit tracking and pupillary constriction. Deepfakes are detected by identifying a rendering-latency gap that causes a mismatch in these biological responses.
Datasets
UNKNOWN
Model(s)
UNKNOWN
Author countries
USA
← Previous
Next →