作者: Matthew Hayes , Andrew Walenstein , Arun Lakhotia
DOI: 10.1007/S11416-008-0100-6
关键词:
摘要: A malware phylogeny model is an estimation of the derivation relationships between a set samples. Systems that construct models are expected to be useful for analysts. While several such systems have been proposed, little known about consistency their results on different data sets, generalizability across types evolution. This paper explores these issues using two artificial history generators: simulate evolution according models. quantitative study was conducted construction and multiple samples High variability found in quality were shown sensitive characteristics sets. The call into question adequacy evaluations typical field, raise pragmatic concerns tool choice analysts, underscore important role model-based simulation play evaluating selecting suitable systems.