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

Ivan Homoliak, Martin Teknös, Martín Ochoa, Dominik Breitenbacher, Saeid Hosseini, Petr Hanacek · ICST Transactions on Security and Safety · 2019

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

Read the paper · More papers on PaperTik