In cybersecurity it is often the case that malicious or anomalous activity can only be detected by combining many weak indicators of compromise, any one of which may not raise suspicion when taken alone. The path that such indicators take can also be critical. This makes the problem of analysing cybersecurity data particularly well suited to Topological Data Analysis (TDA), a field that studies the high level structure of data using techniques from algebraic topology, both for exploratory analysis and as part of a machine learning workflow. By introducing TDA and reviewing the work done on its application to cybersecurity, we hope to highlight to researchers a promising new area with strong potential to improve cybersecurity data science.
翻译:在网络安全方面,经常出现的情况是,恶意或异常活动只能通过将许多薄弱的妥协指标结合起来才能发现,其中任何一个指标单独采用可能不会引起怀疑。这些指标所走的道路也可能至关重要。这使得分析网络安全数据的问题特别适合地形数据分析。 地形数据分析是一个研究高层次数据结构的领域,利用代数表层技术进行数据研究,既用于探索性分析,也作为机器学习工作流程的一部分。通过介绍TDA并审查在网络安全应用方面所做的工作,我们希望向研究人员强调一个有巨大潜力改进网络安全数据科学的有希望的新领域。