Impact of daily computer usage on GUI usage analysis

  • Authors:
  • Eric S Imsand;John A Hamilton, Jr.

  • Affiliations:
  • Auburn University;Auburn University

  • Venue:
  • Proceedings of the 4th annual conference on Information security curriculum development
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper investigates a new method for detecting masquerade attacks. A masquerade attack is a form of attack wherein the attacker uses someone else's identity or one system assumes the identity of another system. One extremely simple and dangerous form of a masquerade attack occurs when an attacker begins using an unattended and unlocked computer. In this paper, we present a new method for detecting this type of masquerade attack, based on the notion of how the current user interacts with the graphical user interface. This method does not use mouse movements or keystroke dynamics, rather profiles how the user manipulates the windows, icons, menus, and pointers that comprise a graphical user interface. In order to evaluate the performance of our method, we conducted some empirical studies in a real operational environment. We consider previously published results and present new analysis concerning the impact of several key demographical factors on the effectiveness of GUI Usage Analysis. Our results indicate that the effectiveness of GUI Usage Analysis is greater in several groups, particularly on users who spend greater amounts of time operating a computer system on an average day.