LTRDetector: Exploring Long-Term Relationship for Advanced Persistent Threats Detection

TL;DR

LTRDetector is a novel framework for detecting advanced persistent threats by analyzing long-term relationships in system provenance graphs, effectively identifying zero-day exploits without relying on predefined signatures.

Contribution

It introduces an innovative graph embedding technique and a holistic approach to capture long-term contextual information for APT detection, including zero-day threats.

Findings

Outperforms existing state-of-the-art APT detection methods

Effective in detecting zero-day exploits without predefined signatures

Validated on five prominent datasets

Abstract

Advanced Persistent Threat (APT) is challenging to detect due to prolonged duration, infrequent occurrence, and adept concealment techniques. Existing approaches primarily concentrate on the observable traits of attack behaviors, neglecting the intricate relationships formed throughout the persistent attack lifecycle. Thus, we present an innovative APT detection framework named LTRDetector, implementing an end-to-end holistic operation. LTRDetector employs an innovative graph embedding technique to retain comprehensive contextual information, then derives long-term features from these embedded provenance graphs. During the process, we compress the data of the system provenance graph for effective feature learning. Furthermore, in order to detect attacks conducted by using zero-day exploits, we captured the system's regular behavior and detects abnormal activities without relying on predefined attack signatures. We also conducted extensive evaluations using five prominent datasets, the efficacy evaluation of which underscores the superiority of LTRDetector compared to existing state-of-the-art techniques.