Correlate the Advanced Persistent Threat Alerts and Logs for Cyber Situation Comprehension

Abstract

With the emerging of the Advanced Persistent Threat (APT) attacks, many high-level information systems have faced a large number of serious threats with characteristics of concealment, permeability, and pertinence. However, existing methods and technologies cannot provide comprehensive and promptly recognition for APT attack activities. To address this problem, we propose an APT Alerts and Logs Correlation Method, named APTALCM, to achieve the cyber situation comprehension. We firstly proposed a cyber situation ontology for modeling the concepts and properties to formalize APT attack activities; For recognize the APT attack intentions we also proposed a cyber situation instances similarity measures method based on SimRank method. Combining with instance similarity, we proposed the APT alert instances correlation method to reconstruct APT attack scenarios and the APT log instances correlation method to detect log instance communities. Through the coalescent of these methods, APTALCM can accomplish the cyber situation comprehension effectively by recognizing the APT attack intentions. The exhaustive experimental results show that the two kernel modules, i.e., Alert Instance Correlation Module (AICM) and Log Instance Correlation Module (LICM) in our APTALCM can achieve a high true positive rate and a low false positive rate.