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

Homoliak, Ivan; Teknös, Martin; Ochoa, Martín; Breitenbacher, Dominik; Hosseini, Saeid; Hanacek, Petr

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

Homoliak, Ivan and Teknös, Martin and Ochoa, Martín and Breitenbacher, Dominik and Hosseini, Saeid and Hanacek, Petr (2018) Improving Network Intrusion Detection Classiﬁers by Non-payload-Based Exploit-Independent Obfuscations: An Adversarial Approach. EAI Endorsed Transactions on Security and Safety.

PDF
29020.pdf
Download (1MB)

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. Th

Item Type:	Article
Date Deposited:	04 Mar 2026 11:38
Last Modified:	12 Apr 2026 06:18
URI:	http://eprints.eai.eu/id/eprint/20048

Actions (login required)

: View Item