arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.15708cs.CR
收藏

动态建模异构高阶交互用于事件过滤中的恶意行为检测

Dynamically Modelling Heterogeneous Higher-Order Interactions for Malicious Behavior Detection in Event Logs

Corentin Larroche, Johan Mazel, Stephan Clémençon

摘要:

事件日志中的异常检测是企业网入侵检测的一种很有前途的方法。通过建立通常活动的统计模型,它旨在检测多种恶意行为,包括旨在逃避基于签名的检测系统的隐形策略,技术和程序(TTP)。然而,找到合适的事件日志异常检测方法仍然是一个重要的挑战。这是由于数据的非常复杂、多方面的性质:事件日志不仅是组合的,而且是时间和异构的数据,因此它们在大多数异常检测的理论框架中都不适合。大多数以前的研究集中在这三个方面之一,建立一个简化的数据表示,可以提供给标准的异常检测算法。相比之下,我们建议通过专门定制的统计模型同时解决所有这三个特征。我们介绍了\textsc{Decades},一个\underline{d}的代理,h \underline{e}异构和\underline{c}组合模型的\underline{a}正常\underline{d}检测\underline{e}事件\underline{s}流,我们证明了它的有效性检测恶意行为通过一个真实的数据集上包含标记的红队活动。特别是,我们通过将我们的模型与依赖于各种数据表示的最先进的基线进行比较,从经验上强调了处理数据的多个特征的重要性。

英文摘要:

Anomaly detection in event logs is a promising approach for intrusion detection in enterprise networks. By building a statistical model of usual activity, it aims to detect multiple kinds of malicious behavior, including stealthy tactics, techniques and procedures (TTPs) designed to evade signature-based detection systems. However, finding suitable anomaly detection methods for event logs remains an important challenge. This results from the very complex, multi-faceted nature of the data: event logs are not only combinatorial, but also temporal and heterogeneous data, thus they fit poorly in most theoretical frameworks for anomaly detection. Most previous research focuses on either one of these three aspects, building a simplified representation of the data that can be fed to standard anomaly detection algorithms. In contrast, we propose to simultaneously address all three of these characteristics through a specifically tailored statistical model. We introduce \textsc{Decades}, a \underline{d}ynamic, h\underline{e}terogeneous and \underline{c}ombinatorial model for \underline{a}nomaly \underline{d}etection in \underline{e}vent \underline{s}treams, and we demonstrate its effectiveness at detecting malicious behavior through experiments on a real dataset containing labelled red team activity. In particular, we empirically highlight the importance of handling the multiple characteristics of the data by comparing our model with state-of-the-art baselines relying on various data representations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑