LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems

TL;DR

This paper introduces a novel system-call language model combined with an ensemble classifier to improve the accuracy and robustness of host-based intrusion detection systems, reducing false alarms and enhancing portability.

Contribution

It presents a new language-modeling approach for system calls and a novel ensemble method to improve anomaly detection accuracy and reduce false alarms.

Findings

Effective detection on benchmark datasets

Reduced false alarm rates

High portability of the model

Abstract

In computer security, designing a robust intrusion detection system is one of the most fundamental and important problems. In this paper, we propose a system-call language-modeling approach for designing anomaly-based host intrusion detection systems. To remedy the issue of high false-alarm rates commonly arising in conventional methods, we employ a novel ensemble method that blends multiple thresholding classifiers into a single one, making it possible to accumulate 'highly normal' sequences. The proposed system-call language model has various advantages leveraged by the fact that it can learn the semantic meaning and interactions of each system call that existing methods cannot effectively consider. Through diverse experiments on public benchmark datasets, we demonstrate the validity and effectiveness of the proposed method. Moreover, we show that our model possesses high portability, which is one of the key aspects of realizing successful intrusion detection systems.