What is it about?
In this paper, we examine the performance of container-based anomaly detection systems for detecting intrusions in multi-tenant applications. We explore the use of the "Bag of System Calls" (BoSC) method along with a sliding window technique and test eight machine learning algorithms for classifying intrusions. Our results show that the best performance comes from the Decision Tree and Random Forest algorithms, both achieving an F-Measure of 99.8% with a sliding window size of 30 and the BoSC method. However, we also find that the Decision Tree algorithm is faster and uses less CPU and memory compared to Random Forest.
Featured Image
Photo by Adi Goldstein on Unsplash
Read the Original
This page is a summary of: Performance Evaluation of Container-Level Anomaly-Based Intrusion Detection Systems for Multi-Tenant Applications Using Machine Learning Algorithms, August 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3465481.3470066.
You can read the full text:
Contributors
The following have contributed to this page
