| Title |
Fractal dimensionality of network traffic as a feature for intrusion detection / |
| Authors |
Bulavas, Viktoras |
| DOI |
10.15388/Proceedings.2019.8 |
| ISBN |
9786090703243 |
| eISBN |
9786090703250 |
| Full Text |
|
| Is Part of |
11th international workshop on data analysis methods for software systems (DAMSS 2019), Druskininkai, Lithuania, November 28-30, 2019 / Lithuanian Computer Society, Vilnius University Institute of Data Science and Digital Technologies, Lithuanian Academy of Sciences.. Vilnius : Vilnius University Press, 2019. p. 16.. ISBN 9786090703243. eISBN 9786090703250 |
| Keywords [eng] |
Information security ; Intrusion detection ; Machine learning ; Minkowski–Bouligand dimension ; Box-counting Fractal dimension ; Higuchi algorithm |
| Abstract [eng] |
Cyber threats are an evolving aspect of our daily lives, intrusion detection being one of the remedies to address information security breach. Intrusion detection relies on observation of network traffic features and their dynamics in time, which allows intrusion detection systems to prevent certain types of attacks upon detection. While rule based systems are following decision trees of prescribed conditions, anomaly recognition systems await for deviation from usual behavior of network users. While multiple event counters help rule-based recognition, various aggregates are calculated in order to detect anomalies. In this research author studies the use of Minkowski–Bouligand dimension, also known as a box-counting fractal dimension, calculated according to T. Higuchi algorithm, as a possible indicator of cyber attack. |
| Published |
Vilnius : Vilnius University Press, 2019 |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2019 |
| CC license |
|
