Publication detail

Improving Network Intrusion Detection Classifiers by Non-payload-Based Exploit-Independent Obfuscations: An Adversarial Approach

HOMOLIAK, I. TEKNŐS, M. BREITENBACHER, D. HANÁČEK, P.

Original Title

Improving Network Intrusion Detection Classifiers by Non-payload-Based Exploit-Independent Obfuscations: An Adversarial Approach

Type

journal article - other

Language

English

Original Abstract

Machine-learning based intrusion detection classifiers are able to detect unknown attacks, but at the same time they may be susceptible to evasion by obfuscation techniques. An adversary intruder which possesses a crucial knowledge about a protection system can easily bypass the detection module. The main objective of our work is to improve the performance capabilities of intrusion detection classifiers against such adversaries. To this end, we firstly propose several obfuscation techniques of remote attacks that are based on the modification of various properties of network connections; then we conduct a set of comprehensive experiments to evaluate the effectiveness of intrusion detection classifiers against obfuscated attacks. We instantiate our approach by means of a tool, based on NetEm and Metasploit, which implements our obfuscation operators on any TCP communication. This allows us to generate modified network trac for machine learning experiments employing features for assessing network statistics and behavior of TCP connections. We perform evaluation on five classifiers: Gaussian Nave Bayes, Gaussian Nave Bayes with kernel density estimation, Logistic Regression, Decision Tree, and Support Vector Machines. Our experiments confirm the assumption that it is possible to evade the intrusion detection capability of all classifiers trained without prior knowledge about obfuscated attacks, causing an exacerbation of the TPR ranging from 7.8% to 66.8%. Further, when widening the training knowledge of the classifiers by a subset of obfuscated attacks, we achieve a significant improvement of the TPR by 4.21% - 73.3%, while the FPR is deteriorated only slightly (0.1% - 1.48%). Finally, we test the capability of an obfuscations-aware classifier to detect unknown obfuscated attacks, where we achieve over 90% detection rate on average for most of the obfuscations.

Keywords

Classification-Based Intrusion Detection, Adversarial Classification, Non-Payload-Based Obfuscation, Evasion, NetEm, Network Normalizer

Authors

HOMOLIAK, I.; TEKNŐS, M.; BREITENBACHER, D.; HANÁČEK, P.

Released

21. 12. 2018

ISBN

2032-9393

Periodical

EAI Endorsed Transactions on Security and Safety

Year of study

5

Number

17

State

Kingdom of Belgium

Pages from

1

Pages to

15

Pages count

15

URL

BibTex

@article{BUT155121,
  author="Ivan {Homoliak} and Martin {Teknős} and Dominik {Breitenbacher} and Petr {Hanáček}",
  title="Improving Network Intrusion Detection Classifiers by Non-payload-Based Exploit-Independent Obfuscations: An Adversarial Approach",
  journal="EAI Endorsed Transactions on Security and Safety",
  year="2018",
  volume="5",
  number="17",
  pages="1--15",
  doi="10.4108/eai.10-1-2019.156245",
  issn="2032-9393",
  url="http://eudl.eu/doi/10.4108/eai.10-1-2019.156245"
}