BASS: an adaptive sleeping scheme for wireless sensor network with bursty arrival
Proceedings of the 2006 international conference on Wireless communications and mobile computing
Anomaly detection in wireless sensor networks: A survey
Journal of Network and Computer Applications
Detecting unknown attacks in wireless sensor networks using clustering techniques
HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part I
Self-Organizing maps versus growing neural gas in detecting data outliers for security applications
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part II
Hi-index | 0.00 |
We introduce a real-time, node-based anomaly detection algorithm that observes the arrival processes experienced by a sensor node. Sensor nodes are resource constrained from many aspects. However, they have specific properties such as lack of mobility and relatively predictable traffic patterns that allows for detection of anomalies in their networking behavior. We develop a new arrival model for the traffic that can be received by a sensor node and devise a scheme to detect anomalous changes in this arrival process. Our detection algorithm keeps short-term dynamic statistics using a multi-level, sliding window event storage scheme. In this algorithm, arrival processes at different time scales are compared using node resourcewise computable, low-complexity, aggregate features.