Título:
DC-VAE, Fine-grained anomaly detection in multivariate time-series with dilated convolutions and variational auto encoders
Otros títulos:
Coordinador:
Director:
Compilador:
Autor:
García González, Gastón
Martínez Tagliafico, Sergio
Fernández, Alicia
Gómez, Gabriel
Acuña, José
Casas, Pedro
Martínez Tagliafico, Sergio
Fernández, Alicia
Gómez, Gabriel
Acuña, José
Casas, Pedro
Tutor:
Tipo de documento:
Ponencia
Editor:
Palabras clave:
Anomaly Detection
Deep Learning
Multivariate Time-Series
Dilated Convolution
VAE
Deep Learning
Multivariate Time-Series
Dilated Convolution
VAE
Descriptores:
Año de publicación:
2022
Contenido:
Resumen:
Due to its unsupervised nature, anomaly detection plays a central role in cybersecurity, in particular on the detection of unknown attacks. A major source of cybersecurity data comes in the form of multivariate time-series (MTS), representing the temporal evolution of multiple, usually correlated measurements. Despite the many approaches available in the literature for time-series anomaly detection, the automatic detection of abnormal events in MTS remains a complex problem. In this paper we introduce DC-VAE, a novel approach to anomaly detection in MTS, leveraging convolutional neural networks (CNNs) and variational auto encoders (VAEs). DC-VAE detects anomalies in time-series data, exploiting temporal information without sacrificing computational and memory resources. In particular, instead of using recursive neural networks, large causal filters, or many layers, DC-VAE relies on Dilated Convolutions (DC) to capture long and short term phenomena in the data, avoiding complex and less-efficient deep architectures, simplifying learning. We evaluate DC-VAE on the detection of anomalies on a large-scale, multi-dimensional network monitoring dataset collected at an operational mobile Internet Service Provider (ISP), where anomalous events were manually labeled during a time span of 7-months, at a five-minutes granularity. Results show the main properties and advantages introduced by VAEs for time-series anomaly detection, as well as the out-performance of dilated convolutions as compared to standard VAEs for time-series modeling.
Descripción:
Transferencia tecnológica. Grupo de investigación Detección de anomalías en series de tiempo, Facultad de Ingeniería. Instituto de Ingeniería Eléctrica.
metadata.articulos.dc.description.uri:
Editorial:
IEEE
EN:
7th International Workshop on Traffic Measurements for Cybersecurity (WTMC 2022), Genoa, Italy, jun 6 2022, pp 1-7
Financiadores:
Este trabajo ha sido parcialmente financiado por la ANII-FMV, proyecto con referencia FMV-1-2019-1-155850 Detección de anomalías en sistemas de telecomunicaciones mediante métodos de aprendizaje continuo, por Telefónica, y por la Austrian FFG ICTof- the-Future project DynAISEC – Adaptive AI/ML for Dynamic Cybersecurity Systems. Gastón García fue apoyado por la beca ANII POS-FMV-2020-1-1009239, y por CSIC, en el marco del programa Movilidad e Intercambios Académicos 2022.
Citación:
García González, G., Martínez Tagliafico, S., Fernández, A. y otros. DC-VAE, Fine-grained anomaly detection in multivariate time-series with dilated convolutions and variational auto encoders [en línea]. EN: 7th International Workshop on Traffic Measurements for Cybersecurity (WTMC 2022), Genoa, Italy, jun 6 2022 , pp 1-7. Piscataway, NJ : IEEE, 2022.
Citación:
metadata.articulos.cc.license.name:
ISBN:
e-ISBN:
ISSN:
ISMN:
Otros identificadores:
Cobertura geográfica:
Cobertura temporal:
Departamento académico:
Grupo de investigación:
Licencia:
Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)
| Ficheros | Descripción | Tamaño | Formato | ||
|---|---|---|---|---|---|
| GMFGAC22.pdf | Camera-Ready | 1.46 MB | Adobe PDF |