2134/14106 Francisco Aparicio-Navarro Francisco Aparicio-Navarro Kostas Kyriakopoulos Kostas Kyriakopoulos David Parish David Parish An automatic and self-adaptive multi-layer data fusion system for WiFi attack detection Loughborough University 2014 Basic probability assignment Data fusion Dempster-Shafer Multi-layer measurements Spoofing attacks WiFi Mechanical Engineering not elsewhere classified 2014-02-06 16:36:18 Journal contribution https://repository.lboro.ac.uk/articles/journal_contribution/An_automatic_and_self-adaptive_multi-layer_data_fusion_system_for_WiFi_attack_detection/9568160 Wireless networks are becoming susceptible to increasingly more sophisticated threats. Most of the current intrusion detection systems (IDSs) that employ multi-layer techniques for mitigating network attacks offer better performance than IDSs that employ single layer approach. However, few of the current multi-layer IDSs could be used off-the-shelf without prior thorough training with completely clean datasets or a fine tuning period. Dempster-Shafer theory has been used with the purpose of combining beliefs of different metric measurements across multiple layers. However, an important step to be investigated remains open; this is to find an automatic and self-adaptive process of basic probability assignment (BPA). This paper describes a novel BPA methodology able to automatically adapt its detection capabilities to the current measured characteristics, without intervention from the IDS administrator. We have developed a multi-layer-based application able to classify individual network frames as normal or malicious with perfect detection accuracy. Copyright © 2013 Inderscience Enterprises Ltd.