No abstract

With the development of the Internet-of-Things (IoT), wireless network security has more and more attention paid to it. The Sybil attack is one of the famous wireless attacks that can forge wireless devices to steal information from clients. These forged devices may constantly attack target access points to crush the wireless network. In this paper, we propose a novel Sybil attack detection based on Channel State Information (CSI). This detection algorithm can tell whether the static devices are Sybil attackers by combining a self-adaptive multiple signal classification algorithm with the Received Signal Strength Indicator (RSSI). Moreover, we develop a novel tracing scheme to cluster the channel characteristics of mobile devices and detect dynamic attackers that change their channel characteristics in an error area. Finally, we experiment on mobile and commercial WiFi devices. Our algorithm can effectively distinguish the Sybil devices. The experimental results show that our Sybil attack detection system achieves high accuracy for both static and dynamic scenarios. Therefore, combining the phase and similarity of channel features, the multi-dimensional analysis of CSI can effectively detect Sybil nodes and improve the security of wireless networks.

An unsupervised machine learning based anomaly detection system by hierarchical temporal memory(HTM) based learning algorithm is proposed to enhance the security of vehicular network. Firstly,the frequency distribution of Controller Area Network (CAN) packets is extracted as a meaningfulfeature to detect attacks in the CAN traffic. Then the features of CAN packets are learned byHTM-based module to predict what it expects to happen next. Furthermore, a novel anomaly scoreis calculated to analyze the probability of each class to discriminate normal and attack status. Thesystem protects vehicles by monitoring the CAN bus to detect threats in real time, including detectinganomalies that might indicate a sophisticated adversary hiding in the vehicle’s systems. Finally, it isdemonstrated with experimental results that the proposed method can provide a real-time anomalydetection to the attack in vehicular network.

No abstract

No abstract