Jamming attack is a serious security threat in wireless sensor networks. Therefore, it is important to frame a mechanism to protect wireless sensor networks from various jamming attacks. Jammer intrusion detection and jamming detection are two separate issues. In this paper, a novel jammer detection framework to detect the intrusion of jammer and the presence of jamming in a cluster-based wireless sensor network is proposed. The proposed framework is novel in three aspects: whenever the cluster head receives a packet, it first verifies whether the source node is a legitimate, new node, or a jammer node. Second, when the source node is declared as a new one in the first step, then the framework validates whether the new node is legitimate node in the previous cluster or a jammer node by using cluster head code. Third, the framework observes the behavior of the newly joined node and the existing nodes to identify whether the nodes in the cluster is jammed or not. Additionally, it also classifies the types of jamming, if the presence of jamming is detected. Simulation result shows that the proposed framework performs extremely well and achieves jamming detection rate as high as 99.88 %.

With its continuous improvements, the cloud computing system leaves an open door for malicious activities. This promotes the significance of constructing a malware action detection component to discover the anomalies in the virtual environment. Besides, the traditional intrusion detection system does not suit for the cloud environment. So, the proposed scheme develops an anomaly detection system, named Hypervisor Detector at a hypervisor layer to detect the abnormalities in the virtual network. Besides, the fuzzy systems have the ability to detect the presence of uncertain and imprecise nature of anomalies; they are not able to construct models based on target data. One of the successful approaches, which integrate fuzzy systems with adaptation and learning proficiencies of a neural network, such as ANFIS Adaptive Neuro Fuzzy Inference System model, is based on target values. The Hypervisor Detector is designed and developed with an ANFIS and practised with a hybrid algorithm, a combination of the back propagation gradient descent technique with the least square method. For the experiments and performance analysis, DARPA's KDD cup data set is used. The performance analysis and results show that the model proposed is well designed to detect the abnormalities in virtual environment with the minimum false alarm rate and reduced overhead.

Internet of things (IoT) comprises many heterogeneous nodes that operate together to accomplish a human friendly or a business task to ease the life. Generally, IoT nodes are connected in wireless media and thus they are prone to jamming attacks. In the present scenario jamming detection (JD) by using machine learning (ML) algorithms grasp the attention of the researchers due to its virtuous outcome. In this research, jamming detection is modelled as a classification problem which uses several features. Using one/two or minimum number of features produces vague results that cannot be explained. Also the relationship between the feature and the class label cannot be efficiently determined, specifically, if the chosen number of features for training is minimum (say 1 or 2). To obtain good results, machine-learning algorithms are trained by large number of data sets. However, collection of large number of datasets to solve jamming detection is not easy and most of the times generation and collection of large data sets become paradigmatic. In this paper, to solve this problem, more number of features with nominal number of data’s is considered that eases the data collection and the classification accuracy. In this research, an efficient technique based on locality sensitive hashing (LSH) for K-nearest neighbor algorithm (K-NN), which takes less time for constructing and querying the hash table that gives good accuracy is proposed and evaluated. From the results, it is clear that the obtained results are validatable and the model is more sensible.