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 manage
the huge amounts of data coming from sensors. To ensure the proper operation of next-generation
electricity grids, the captured data must be reliable and protected against vulnerabilities and
possible attacks. The contribution of this paper to the state of the art lies in the identification of
cyberattacks that produce anomalous behaviour in network management protocols. A novel neural
projectionist technique (Beta Hebbian Learning, BHL) has been employed to get a general visual
representation of the traffic of a network, making it possible to identify any abnormal behaviours and
patterns, 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 other
state-of-the-art methods.
