Physiological Synchrony: A New Approach Toward Identifying Unknown Presentation Attacks on Biometric Systems
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Presentation attacks are falsified biometric traits presented on biometric systems to deceive them. While biometric systems can be tuned and modified to reliably detect known presentation attacks, their performance significantly degrades when encountering unknown presentation attacks. In this article, we propose a new approach toward detecting unknown presentation attacks based on the measurement and characterization of synchrony between multiple physiological signals obtained from contact and contactless sensors. Synchrony between two physiological signals was captured by analyzing the blood flow dynamics and respiration patterns. The instantaneous phase difference between two physiological signals was represented as a phase vector using the Hilbert transform and the degree of phase coherence defined as the absolute mean of phase vectors over the analysis period was used as a measure of synchrony. A weighted k-nearest neighbors (k-NN) classifier was then designed to detect valid and invalid biometric presentations based on the degree of phase coherence. The proposed method was validated on the detection of synchrony between two respiration patterns obtained through the measurement of chest movements using an ultrawideband (UWB) radar and respiratory sinus arrhythmia (RSA) using a finger photoplethysmogram sensor on data collected from 50 individuals. It achieved a high accuracy of 95.3%, a sensitivity of 96%, and a specificity of 94% in detecting corrupted and nonsynchronous patterns that did not contain valid respiration signatures. The proposed method shows promise toward improving the reliability of biometric systems in the detection of unknown and sophisticated attacks that may spoof one or more of the presented biometrics.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it