Detecting Unknown Attacks in Wireless Sensor Networks Using Clustering Techniques

Abstract

Wireless sensor networks are usually deployed in unattended environments. This is the main reason why the update of security policies upon identifying new attacks cannot be done in a timely fashion, which gives enough time to attackers to make significant damage. Thus, it is of great importance to provide protection from unknown attacks. However, existing solutions are mostly concentrated on known attacks. In order to tackle this issue, we propose a machine learning solution for anomaly detection along with the feature extraction process that tries to detect temporal and spatial inconsistencies in the sequences of sensed values and the routing paths used to forward these values to the base station. The data produced in the presence of an attacker are treated as outliers, and detected using clustering techniques. The techniques are coupled with a reputation system, isolating in this way the compromised nodes. The proposal exhibits good performances in detecting and confining previously unseen attacks.