Exploring the use of fitness landscape analysis for understanding malware evolution
Kehinde O. Babaagba, Ritwik Murali, Sarah L. Thomson · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2024
We conduct a preliminary study exploring the potential of using fitness landscape analysis for understanding the evolution of malware. This type of optimisation is fairly new and has not previously been studied through the lens of landscape analysis. We consider Android-based malware evolution and an existing evolutionary algorithm from the literature is used. We construct and visualise search trajectory networks (STNs), which are a new tool aimed at investigation of algorithm behaviour. The STNs indicate that the considered malware spaces may be difficult to navigate under current search operators and that new ones may warrant consideration.