Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Peer-to-Peer Wireless LAN Consortia: Economic Modeling and Architecture
P2P '03 Proceedings of the 3rd International Conference on Peer-to-Peer Computing
Effective use of reputation in peer-to-peer environments
CCGRID '04 Proceedings of the 2004 IEEE International Symposium on Cluster Computing and the Grid
Trust-based security for wireless ad hoc and sensor networks
Computer Communications
Linear-Time Computation of Similarity Measures for Sequential Data
The Journal of Machine Learning Research
Attacks and defenses of ubiquitous sensor networks
Attacks and defenses of ubiquitous sensor networks
Performance evaluation of density-based clustering methods
Information Sciences: an International Journal
Location verification based defense against sybil attack in sensor networks
ICDCN'06 Proceedings of the 8th international conference on Distributed Computing and Networking
Hi-index | 0.00 |
In this article we propose to couple reputation systems for wireless sensor networks with a genetic algorithm in order to improve their time of response to adversarial activities. The reputation of each node is assigned by an unsupervised genetic algorithm trained for detecting outliers in the data. The response of the system consists in assigning low reputation values to the compromised nodes cutting them off from the rest of the network. The genetic algorithm uses the feature extraction process that does not capture the properties of the attacks, but rather relies on the existing temporal and spatial redundancy in sensor networks and 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. This solution offers many benefits: scalable solution, fast response to thwart activities, ability to detect unknown attacks, high adaptability, and high ability in detecting and confining attacks. Comparing to the standard clustering algorithms, the benefit of this one is that it is not necessary to assign the number of clusters from the beginning. The solution is also robust to both parameter changes and the presence of large amounts of malicious data in the training and testing datasets.