Non-intrusive anomaly detection for encrypted networks

The use of encryption is steadily increasing. Packet payloads that are encrypted are becoming increasingly difficult to analyze using IDSs. This investigation uses a new non-intrusive IDS approach to detect network intrusions using a K-Means clustering methodology. It was found that this approach was able to detect many intrusions for these datasets while maintaining the encrypted confidentiality of packet information. This work utilized the KDD '99 and NSL-KDD evaluation datasets for testing.

Name thesis:degree_name

MS

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Lane Department of Computer Science and Electrical Engineering

Year dc:date.available

2014

Author dc:creator

• Armendariz Jr., Luis C.

Contributors dc:contributor

• Roy S. Nutter
• Katerina D. Goseva-Popstojanova
• Afzel Noore.

• Computer science
• Computer engineering
• Information technology

Identifier

https://researchrepository.wvu.edu/etd/111

OAI identifier oai:identifier

oai:researchrepository.wvu.edu:etd-1114