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
N1 - Funding Information:
∗This work has been partly funded by CNS grant #1218505, IIS grant #1116385, and NIH grant #EB019202.
Publisher Copyright:
© 2017 IEEE.
PY - 2017
Y1 - 2017
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
T3 - Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
SP - 1045
EP - 1048
BT - Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
A2 - Chen, Xuewen
A2 - Luo, Bo
A2 - Luo, Feng
A2 - Palade, Vasile
A2 - Wani, M. Arif
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017
Y2 - 18 December 2017 through 21 December 2017
ER -