Performance and security strength trade-off in machine learning based biometric authentication systems

Koosha Sadeghi, Ayan Banerjee, Javad Sohankar, Sandeep Gupta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In Biometric Authentication Systems (BAS), the variability amongst population biometric data ensures distinctiveness, and helps minimizing false acceptance of non-subject data. However, higher variability implies temporal variations for a given subject, which can potentially reject subject data. Such variations are suppressed using feature extraction and Machine Learning (ML) techniques for improving the performance, but also reduce the adversary's effort in breaking the system (security strength) using forged data. Typically for BAS design, performance and security strength are evaluated in isolation using experimental analysis. This research provides an analytical approach to evaluate the BAS performance and strength, and their trade-off, by modeling the biometric data, and studying the effect of feature extraction and ML configurations on processing the data. Experimental analysis on 106 subjects' brain signal validates the analytical methodology results.

Original languageEnglish (US)
Title of host publicationProceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1045-1048
Number of pages4
Volume2018-January
ISBN (Electronic)9781538614174
DOIs
StatePublished - Jan 16 2018
Event16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 - Cancun, Mexico
Duration: Dec 18 2017Dec 21 2017

Other

Other16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
CountryMexico
CityCancun
Period12/18/1712/21/17

Fingerprint

Biometrics
Authentication
Learning systems
Feature extraction
Security systems
Brain
Systems analysis
Processing

Keywords

  • machine learning
  • performance/security-trade-off

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Sadeghi, K., Banerjee, A., Sohankar, J., & Gupta, S. (2018). Performance and security strength trade-off in machine learning based biometric authentication systems. In Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017 (Vol. 2018-January, pp. 1045-1048). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2017.00-12

Performance and security strength trade-off in machine learning based biometric authentication systems. / Sadeghi, Koosha; Banerjee, Ayan; Sohankar, Javad; Gupta, Sandeep.

Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1045-1048.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sadeghi, K, Banerjee, A, Sohankar, J & Gupta, S 2018, Performance and security strength trade-off in machine learning based biometric authentication systems. in Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1045-1048, 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017, Cancun, Mexico, 12/18/17. https://doi.org/10.1109/ICMLA.2017.00-12
Sadeghi K, Banerjee A, Sohankar J, Gupta S. Performance and security strength trade-off in machine learning based biometric authentication systems. In Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1045-1048 https://doi.org/10.1109/ICMLA.2017.00-12
Sadeghi, Koosha ; Banerjee, Ayan ; Sohankar, Javad ; Gupta, Sandeep. / Performance and security strength trade-off in machine learning based biometric authentication systems. Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1045-1048
@inproceedings{e9a2bd0e3daa4446ad091905c6d1c63c,
title = "Performance and security strength trade-off in machine learning based biometric authentication systems",
abstract = "In Biometric Authentication Systems (BAS), the variability amongst population biometric data ensures distinctiveness, and helps minimizing false acceptance of non-subject data. However, higher variability implies temporal variations for a given subject, which can potentially reject subject data. Such variations are suppressed using feature extraction and Machine Learning (ML) techniques for improving the performance, but also reduce the adversary's effort in breaking the system (security strength) using forged data. Typically for BAS design, performance and security strength are evaluated in isolation using experimental analysis. This research provides an analytical approach to evaluate the BAS performance and strength, and their trade-off, by modeling the biometric data, and studying the effect of feature extraction and ML configurations on processing the data. Experimental analysis on 106 subjects' brain signal validates the analytical methodology results.",
keywords = "machine learning, performance/security-trade-off",
author = "Koosha Sadeghi and Ayan Banerjee and Javad Sohankar and Sandeep Gupta",
year = "2018",
month = "1",
day = "16",
doi = "10.1109/ICMLA.2017.00-12",
language = "English (US)",
volume = "2018-January",
pages = "1045--1048",
booktitle = "Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Performance and security strength trade-off in machine learning based biometric authentication systems

AU - Sadeghi, Koosha

AU - Banerjee, Ayan

AU - Sohankar, Javad

AU - Gupta, Sandeep

PY - 2018/1/16

Y1 - 2018/1/16

N2 - In Biometric Authentication Systems (BAS), the variability amongst population biometric data ensures distinctiveness, and helps minimizing false acceptance of non-subject data. However, higher variability implies temporal variations for a given subject, which can potentially reject subject data. Such variations are suppressed using feature extraction and Machine Learning (ML) techniques for improving the performance, but also reduce the adversary's effort in breaking the system (security strength) using forged data. Typically for BAS design, performance and security strength are evaluated in isolation using experimental analysis. This research provides an analytical approach to evaluate the BAS performance and strength, and their trade-off, by modeling the biometric data, and studying the effect of feature extraction and ML configurations on processing the data. Experimental analysis on 106 subjects' brain signal validates the analytical methodology results.

AB - In Biometric Authentication Systems (BAS), the variability amongst population biometric data ensures distinctiveness, and helps minimizing false acceptance of non-subject data. However, higher variability implies temporal variations for a given subject, which can potentially reject subject data. Such variations are suppressed using feature extraction and Machine Learning (ML) techniques for improving the performance, but also reduce the adversary's effort in breaking the system (security strength) using forged data. Typically for BAS design, performance and security strength are evaluated in isolation using experimental analysis. This research provides an analytical approach to evaluate the BAS performance and strength, and their trade-off, by modeling the biometric data, and studying the effect of feature extraction and ML configurations on processing the data. Experimental analysis on 106 subjects' brain signal validates the analytical methodology results.

KW - machine learning

KW - performance/security-trade-off

UR - http://www.scopus.com/inward/record.url?scp=85048503200&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048503200&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2017.00-12

DO - 10.1109/ICMLA.2017.00-12

M3 - Conference contribution

AN - SCOPUS:85048503200

VL - 2018-January

SP - 1045

EP - 1048

BT - Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -