Advancing Network Security: A Comprehensive Testbed and Dataset for Machine Learning-Based Intrusion Detection

TL;DR

A Testbed designed for generating network traffic, leveraging the capabilities of containers, Kubernetes, and eBPF/XDP technologies is introduced, offering small malicious network traffic dataset publically that satisfy ground truth property completely.

Abstract

This paper introduces a Testbed designed for generating network traffic, leveraging the capabilities of containers, Kubernetes, and eBPF/XDP technologies. Our Testbed serves as an advanced platform for producing network traffic for machine learning based network experiments. By utilizing this Testbed, we offer small malicious network traffic dataset publically that satisfy ground truth property completely.

Figures (6)

• Figure 1: Testbed setup for malicious traffic generation (All Resources obtained from OF@TEIN playground)
• Figure 2: Attack Scenerios
• Figure 3: Attack Scenerios (Large DDoS attack (14 attackers and 6 victims))
• Figure 4: Attack Scenerios (Large DDoS attack (26 attackers and 12 victims))
• Figure 5: DDoS .pcap file from interface vethwe-bridge