Anomaly detection of masquerders based upon typing biometrics and probabilistic neural network

  • Authors:
  • Yingbing Yu

  • Affiliations:
  • Austin Peay State University, Clarksville, TN

  • Venue:
  • Journal of Computing Sciences in Colleges
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper investigates a new method to more effectively detect anomaly intrusions from masqueraders. Typing biometrics of keystroke patterns from users are collected and used as the normal behavior profiles. The supervised learning probabilistic neural network (PNN) is used for the classification of data as from a normal user or from a masquerader. Experimental show the good results with a high rate of successful detection of masqueraders and a low false alarm rate.