Cryptographic Key Generation Method Using Biometrics and Multiple Classification Model

Vol. 28, No. 6, pp. 1427-1437, Nov. 2018
10.13089/JKIISC.2018.28.6.1427, Full Text:
Keywords: biometrics, Cryptosystem, Key-binding scheme, Multiple classifiers
Abstract

While biometric authentication system has been in general use, research is ongoing to apply biometric data to public keyinfrastructure. It is a significant task to generate a cryptographic key from biometrics in setting up a public key of Bio-PKI. Methods for generating the key by quantization of feature vector can cause data loss and degrade the performance of keyextraction. In this paper, we suggest a new method for generating a cryptographic key from classification results ofbiometric data using multiple classifying models. Our proposal does not cause data loss of feature vector so it showed betterperformance in key extraction. Also, it uses the multiple models to generate key blocks which produce sufficient length ofthe key.

Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
이현석, 김혜진, 양대헌, 이경희, "Cryptographic Key Generation Method Using Biometrics and Multiple Classification Model," Journal of The Korea Institute of Information Security and Cryptology, vol. 28, no. 6, pp. 1427-1437, 2018. DOI: 10.13089/JKIISC.2018.28.6.1427.

[ACM Style]
이현석, 김혜진, 양대헌, and 이경희. 2018. Cryptographic Key Generation Method Using Biometrics and Multiple Classification Model. Journal of The Korea Institute of Information Security and Cryptology, 28, 6, (2018), 1427-1437. DOI: 10.13089/JKIISC.2018.28.6.1427.