作者: Arthur Zimek , Peter Schneider-Kamp , Jonas Herskind Sejr
DOI: 10.1109/ICDIS50059.2020.00016
关键词: Pipeline (software) 、 Outlier 、 Pipeline transport 、 Anomaly detection 、 Task analysis 、 Computer security 、 Computer science 、 Internet security 、 Zero (linguistics) 、 Service (systems architecture)
摘要: The detection of malicious HTTP(S) requests is a pressing concern in cyber security, particular given the proliferation HTTP-based (micro-)service architectures. In addition to rule-based systems for known attacks, anomaly has been shown be promising approach unknown (zero-day) attacks. This article extends existing work by integrating outlier explanations individual into an end-to-end pipeline. These reflect internal working Empirically, we show that found coincide with manually labelled identified outliers, allowing security professionals quickly identify and understand requests.