• Skip to primary navigation
  • Skip to main content
SRI logo
  • About
    • Press room
  • Expertise
    • Advanced imaging systems
    • Artificial intelligence
    • Biomedical R&D services
    • Biomedical sciences
    • Computer vision
    • Cyber & formal methods
    • Education and learning
    • Innovation strategy and policy
    • National security
    • Ocean & space
    • Quantum
    • QED-C
    • Robotics, sensors & devices
    • Speech & natural language
    • Video test & measurement
  • Ventures
  • NSIC
  • Careers
  • Contact
  • 日本支社
Search
Close
Biomedical sciences publications August 30, 2021

Physiological Synchrony: A New Approach Toward Identifying Unknown Presentation Attacks on Biometric Systems

SRI authors: Fiona C Baker, Massimiliano de Zambotti, Bing-Bing Chai

Citation

Copy to clipboard


Mohamad Forouzanfar; Fiona C. Baker; Massimiliano De Zambotti; Stephanie Claudatos; Bing-Bing Chai; James Bergen; Jeffrey Lubin. Physiological Synchrony: A New Approach Toward Identifying Unknown Presentation Attacks on Biometric Systems, in IEEE Transactions on Instrumentation and Measurement, doi: 10.1109/TIM.2021.3107044.

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. Here, 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 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 ultra-wideband radar and respiratory sinus arrhythmia using a finger photoplethysmogram sensor on data collected from 50 individuals. It achieved a high accuracy of 95.3%, sensitivity of 96%, and 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.

↓ View online

Share this

How can we help?

Once you hit send…

We’ll match your inquiry to the person who can best help you.

Expect a response within 48 hours.

Career call to action image

Make your own mark.

Search jobs

Our work

Case studies

Publications

Timeline of innovation

Areas of expertise

Institute

Leadership

Press room

Media inquiries

Compliance

Careers

Job listings

Contact

SRI Ventures

Our locations

Headquarters

333 Ravenswood Ave
Menlo Park, CA 94025 USA

+1 (650) 859-2000

Subscribe to our newsletter


日本支社
SRI International
  • Contact us
  • Privacy Policy
  • Cookies
  • DMCA
  • Copyright © 2022 SRI International