Can Migration-Based Dynamic Platform Technique Work Effectively: A Quantitative Analysis Perspective

Migration-based Dynamic Platform (MdyPlat) is a type of Moving Target Defense (MTD) techniques to protect the task executed on the platform. MdyPlat actively hinders sophisticated attacks through randomly and dynamically setting up a platform for executing the task. This paper aims to investigate how MdyPlat-related factors make quantitative impact on the capability of MdyPlat technique. We develop a semi-Markov model for describing the system dynamics and then derive metric calculation formulas for investigation. Compared to the existing analytical-modeling-based evaluation methods, our modeling approach can work even the times of all MdyPlat-related events follow any type of distribution. The comparison between simulation and numerical results validates the approximate accuracy of the model and formulas. Numerical experiment results uncover that 1) MdyPlat technique can effectively enhance the task security, particularly under high attack intensity; 2) The security risk of the executed task varies in different task-execution scenarios, which are denoted by the number of platforms and the probability distribution of the times of MDP-related events; and 3) Different cumulative distribution function of event time under the same mean value leads to different analysis result of the task security.