HUMAN - Hierarchical Clustering forUnsupervised Anomaly Detection & Interpretation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00342469" target="_blank" >RIV/68407700:21230/20:00342469 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/NoF50125.2020.9249194" target="_blank" >https://doi.org/10.1109/NoF50125.2020.9249194</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/NoF50125.2020.9249194" target="_blank" >10.1109/NoF50125.2020.9249194</a>

Result language

angličtina

Original language name

HUMAN - Hierarchical Clustering forUnsupervised Anomaly Detection & Interpretation

Original language description

The automatic detection and interpretation of network traffic anomalies through machine learning is a well-known problem, for which no general solution is available. Both supervised and unsupervised (i.e., anomaly detection) approaches require prior knowledge on the monitoring data, either in terms of normal operation profiles or on the specific anomalies to detect. As a consequence, both approaches have clear limitations when it comes to detecting, and in particular interpreting, previously unseen events. We present HUMAN, a general hierarchical-clustering-based approach for unsupervised network traffic analysis, which can both detect and interpret anomalous behaviors ina completely black-box manner, without relying on any ground-truth on the system under analysis. HUMAN can detect and interpret complex patterns in the analyzed data, using a structural approach which exploits hierarchical cluster relationships and correlations among features. We describe the building blocks of HUMAN and explain its functioning in detail, using as case study the detection and interpretation of performance issues in major cloud platforms, through the unsupervised analysis of distributed active cloud latency measurements. The HUMAN approach can be applied to the unsupervised analysis of any kind of nested or hierarchically structured multi-dimensional data, showing the potential of hierarchical clustering for general unsupervised data analytics.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

20202 - Communication engineering and systems

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2020

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

11th International Conference on Networks of the Future (NoF 2020)

ISBN

978-1-7281-8055-7

ISSN

—

e-ISSN

—

Number of pages

9

Pages from-to

132-140

Publisher name

IEEE

Place of publication

St. Paul, Minnesota

Event location

Bordeaux

Event date

Oct 12, 2020

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—