Density-Approximating Neural Network Models for Anomaly Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F18%3A00507118" target="_blank" >RIV/67985556:_____/18:00507118 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Density-Approximating Neural Network Models for Anomaly Detection

Popis výsledku v původním jazyce

We propose an alternative use of neural models in anomaly detection. Traditionally, in anomaly detection context the common use of neural models is in form of auto-encoders. Through the use of auto-encoders the true anomality is proxied by reconstruction error. Auto-encoders often perform well but do not guarantee to perform as expected in all cases. A popular more direct way of modeling anomality distribution is through k-Nearest Neighbor models. Although kNN can perform better than auto-encoders in some cases, their applicability can be seriously impaired by their space and time complexity especially with high-dimensional large-scale data. The alternative we propose is to model the distribution imposed by kNN using neural networks. We show that such neural models are capable of achieving comparable accuracy to kNN while reducing computational complexity by orders of magnitude. The de-noising e ect of a neural model with limited number of neurons and layers is shown to lead to accuracy improvements in some cases. We evaluate the proposed idea against standard kNN and auto-encoders on a large set of benchmark data and show that in majority of cases it is possible to improve on accuracy or computational cost.

Název v anglickém jazyce

Density-Approximating Neural Network Models for Anomaly Detection

Popis výsledku anglicky

We propose an alternative use of neural models in anomaly detection. Traditionally, in anomaly detection context the common use of neural models is in form of auto-encoders. Through the use of auto-encoders the true anomality is proxied by reconstruction error. Auto-encoders often perform well but do not guarantee to perform as expected in all cases. A popular more direct way of modeling anomality distribution is through k-Nearest Neighbor models. Although kNN can perform better than auto-encoders in some cases, their applicability can be seriously impaired by their space and time complexity especially with high-dimensional large-scale data. The alternative we propose is to model the distribution imposed by kNN using neural networks. We show that such neural models are capable of achieving comparable accuracy to kNN while reducing computational complexity by orders of magnitude. The de-noising e ect of a neural model with limited number of neurons and layers is shown to lead to accuracy improvements in some cases. We evaluate the proposed idea against standard kNN and auto-encoders on a large set of benchmark data and show that in majority of cases it is possible to improve on accuracy or computational cost.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

ACM SIGKDD 2018 Workshop

ISBN

978-1-4503-5552-0

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

ACM

Místo vydání

New York

Místo konání akce

London

Datum konání akce

20. 8. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—