An ensemble-based approach to the security-oriented classification of low-level log traces

作者：

Highlights：

• We propose to classify traces as insecure/secure based on example logs and securitybreach models

• We face a setting where the traces are sequences of events that do not refer to the modelsactivities

• A meta-classification scheme is used to mix two example-driven classifiers and a modeldriven one

• The proposed framework was empirically proven to improve example- and model- driven approaches

摘要

•We propose to classify traces as insecure/secure based on example logs and securitybreach models•We face a setting where the traces are sequences of events that do not refer to the modelsactivities•A meta-classification scheme is used to mix two example-driven classifiers and a modeldriven one•The proposed framework was empirically proven to improve example- and model- driven approaches

论文关键词：Business process analysis,Process mining,Security,Classification

论文评审过程：Received 7 December 2018, Revised 27 February 2020, Accepted 12 March 2020, Available online 28 March 2020, Version of Record 11 April 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113386