RT info:eu-repo/semantics/article
T1 Intrusion Detection with Unsupervised Techniques for Network Management Protocols over Smart Grids
A1 Vega Vega, Rafael Alejandro
A1 Chamoso, Pablo
A1 González Briones, Alfonso
A1 Casteleiro-Roca, José-Luis
A1 Jove, Esteban
A1 Meizoso-López, María del Carmen
A1 Rodríguez-Gómez, Benigno Antonio
A1 Quintián, Héctor
A1 Herrero Cosío, Álvaro
A1 Matsui, Kenji
A1 Corchado, Emilio
A1 Calvo-Rolle, José Luis
K1 Smart grid
K1 Computational intelligence
K1 Automatic response
K1 Exploratory projection pursuit
K1 Neural network
K1 Informática
K1 Computer science
AB The present research work focuses on overcoming cybersecurity problems in the Smart Grid.Smart Grids must have feasible data capture and communications infrastructure to be able to managethe huge amounts of data coming from sensors. To ensure the proper operation of next-generationelectricity grids, the captured data must be reliable and protected against vulnerabilities andpossible attacks. The contribution of this paper to the state of the art lies in the identification ofcyberattacks that produce anomalous behaviour in network management protocols. A novel neuralprojectionist technique (Beta Hebbian Learning, BHL) has been employed to get a general visualrepresentation of the traffic of a network, making it possible to identify any abnormal behaviours andpatterns, indicative of a cyberattack. This novel approach has been validated on 3 different datasets,demonstrating the ability of BHL to detect different types of attacks, more effectively than otherstate-of-the-art methods.
PB MDPI
YR 2020
FD 2020-03
LK http://hdl.handle.net/10259/7243
UL http://hdl.handle.net/10259/7243
LA eng
NO TEACHING STAFF MOBILITY UNDER BILATERAL AGREEMENTS (University of Salamanca—Osaka Institute of Technology 2019).
DS Repositorio Institucional de la Universidad de Burgos
RD 01-may-2024