The detection of malicious nodes still represents a challenging task in wireless sensor networks. This issue is particularly relevant in data sensitive services. In this work a novel scheme, namely GoNe, is proposed, able to enforce data security and privacy leveraging a machine learning technique based on self organizing maps. GoNe provides an assessment of node reputation scores on a dynamic basis and in presence of multiple kinds of malicious attacks. Its performance has been extensively analized through simulations, which demonstrate its effectiveness in terms of node behavior classification, attack identification, data accuracy, energy efficiency and signalling overhead.
GoNe: Dealing with node behavior / Sicari, Sabrina; Rizzardi, Alessandra; Grieco, Luigi Alfredo; Coen Porisini, Alberto. - (2015), pp. 358-362. (Intervento presentato al convegno 5th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2015 tenutosi a Berlin, Germany nel September 6-9, 2015) [10.1109/ICCE-Berlin.2015.7391280].
GoNe: Dealing with node behavior
GRIECO, Luigi Alfredo;
2015-01-01
Abstract
The detection of malicious nodes still represents a challenging task in wireless sensor networks. This issue is particularly relevant in data sensitive services. In this work a novel scheme, namely GoNe, is proposed, able to enforce data security and privacy leveraging a machine learning technique based on self organizing maps. GoNe provides an assessment of node reputation scores on a dynamic basis and in presence of multiple kinds of malicious attacks. Its performance has been extensively analized through simulations, which demonstrate its effectiveness in terms of node behavior classification, attack identification, data accuracy, energy efficiency and signalling overhead.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
