Event / Presentation Title

Harnessing Predictive Models for Assisting Network Forensic Investigations of DNS Tunnels

Proposal / Submission Type

Peer Reviewed Paper

Abstract

In recent times, DNS tunneling techniques have been used for malicious purposes, however network security mechanisms struggle to detect them. Network forensic analysis has been proven effective, but is slow and effort intensive as Network Forensics Analysis Tools struggle to deal with undocumented or new network tunneling techniques. In this paper, we present a machine learning approach, based on feature subsets of network traffic evidence, to aid forensic analysis through automating the inference of protocols carried within DNS tunneling techniques. We explore four network protocols, namely, HTTP, HTTPS, FTP, and POP3. Three features are extracted from the DNS tunneled traffic: IP packet length, DNS Query Name Entropy, and DNS Query Name Length. We benchmark the performance of four classification models, i.e., decision trees, support vector machines, k-nearest neighbours, and neural networks, on a data set of DNS tunneled traffic. Classification accuracy of 95% is achieved and the feature set reduces the original evidence data size by a factor of 74%. More importantly, our findings provide strong evidence that predictive modeling machine learning techniques can be used to identify network protocols within DNS tunneled traffic in real-time with high accuracy from a relatively small-sized feature-set, without necessarily infringing on privacy from the outset, nor having to collect complete DNS Tunneling sessions.

This document is currently not available here.

Share

COinS
 

Harnessing Predictive Models for Assisting Network Forensic Investigations of DNS Tunnels

In recent times, DNS tunneling techniques have been used for malicious purposes, however network security mechanisms struggle to detect them. Network forensic analysis has been proven effective, but is slow and effort intensive as Network Forensics Analysis Tools struggle to deal with undocumented or new network tunneling techniques. In this paper, we present a machine learning approach, based on feature subsets of network traffic evidence, to aid forensic analysis through automating the inference of protocols carried within DNS tunneling techniques. We explore four network protocols, namely, HTTP, HTTPS, FTP, and POP3. Three features are extracted from the DNS tunneled traffic: IP packet length, DNS Query Name Entropy, and DNS Query Name Length. We benchmark the performance of four classification models, i.e., decision trees, support vector machines, k-nearest neighbours, and neural networks, on a data set of DNS tunneled traffic. Classification accuracy of 95% is achieved and the feature set reduces the original evidence data size by a factor of 74%. More importantly, our findings provide strong evidence that predictive modeling machine learning techniques can be used to identify network protocols within DNS tunneled traffic in real-time with high accuracy from a relatively small-sized feature-set, without necessarily infringing on privacy from the outset, nor having to collect complete DNS Tunneling sessions.