Total views : 138

Score based Decision System for Imposter Identification using Non-Biometric Authentication Factors

Affiliations

  • School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, India

Abstract


Objectives: An imposter identification system allows authenticated user to request for regeneration of password while restricting users who possess imposter properties. Existing system in the literature either allows the users to request for regeneration of password or denies access to the users. So the imposter acceptance and genuine rejection percentage is high in the existing system. Methods: The proposed system improves the performance of imposter identification system by adding three levels of non biometric factors to it. Fuzzy score is calculated on each level and the scores are accumulated with its own weight at last level. Using weighted score the threshold is compared and evaluated to make further decisions. Based on the evaluations made with respect to the threshold, the user will be allowed or denied to regenerate the password. Neural Network is applied to find out the threshold value whereas initially the threshold value is randomly assigned. The neural system works on two modes; one is learning mode in which the developer has to validate the system using training and testing dataset. Findings: With the validation, the threshold value is set to the most accurate value. Secondly, the system works on production mode where the end user uses the system. The proposed system increases the performance of imposter identification algorithm by increasing the rate of genuine user acceptance and imposter rejection. Applications: For all, ID-Password based authentication applications which supports Forget password as a sub module for the authentication module.

Keywords

Bio-metric, Imposter, Neural System.

Full Text:

 |  (PDF views: 118)

References


  • Grover J, Hanmandlu M. Hybrid fusion of score level and adaptive fuzzy decision level fusions for the finger-knuckleprint based authentication. Applied Soft Computing. 2015 Jun; 31:1–13.
  • Murofushi T, Sugeno M. A theory of fuzzy measures: Representations, choquet integral and null sets. Journal of Mathematical Analysis and Applications. 1991 Aug; 159(2):532–49.
  • Dass SC, Nandakumar K, Jain AK. A principled approach to score level fusion in multimodal biometric systems.Springer Berlin Heidelberg; 2005 Jul. p. 1049–58.
  • Gao Y, Maggs M. Feature-level fusion in personal identification.Proceeding of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05); 2005. p. 1–6.
  • Goyal M, Yadav D, Tripathi A. Intuitionist fuzzy genetic weighted averaging operator and its application for multiple attribute decision making in E-Learning. Indian Journal of Science and Technology. 2016 Jan; 9(1):1–15.
  • Ross TJ. Fuzzy logic with engineering applications. 2nd ed.John Wiley and Sons Ltd; 2004 Jun.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.