Integration of the Internet into the entities of the different domains of human society (such as smart homes, health care, smart grids, manufacturing processes, product supply chains, and environmental monitoring) is emerging as a new paradigm called the Internet of Things (IoT). However, the ubiquitous and wide-range IoT networks make them prone to cyberattacks. One of the main types of attack is a denial of service (DoS), where the attacker floods the network with a large volume of data to prevent nodes from using the services. An intrusion detection mechanism is considered a chief source of protection for information and communications technology. However, conventional intrusion detection methods need to be modified and improved for application to the IoT owing to certain limitations, such as resource-constrained devices, the limited memory and battery capacity of nodes, and specific protocol stacks. In this paper, we develop a lightweight attack detection strategy utilizing a supervised machine learning-based support vector machine (SVM) to detect an adversary attempting to inject unnecessary data into the IoT network. The simulation results show that the proposed SVM-based classifier, aided by a combination of two or three incomplex features, can perform satisfactorily in terms of classification accuracy and detection time. INDEX TERMS Intrusion detection system, anomaly detection, Internet of Things, support vector machine. VLADIMIR SHAKHOV (M'09) received the B.S. degree in mechanics and applied mathematics, the M.S. degree in mathematics, and the Ph.D.
The emerging Internet of Things (IoT) has great potential; however, the societal costs of the IoT can outweigh its benefits. To unlock IoT potential, there needs to be improvement in the security of IoT applications. There are several standardization initiatives for sensor networks, which eventually converge with the Internet of Things. As sensor-based applications are deployed, security emerges as an essential requirement. One of the critical issues of wireless sensor technology is limited sensor resources, including sensor batteries. This creates a vulnerability to battery-exhausting attacks. Rapid exhaustion of sensor battery power is not only explained by intrusions, but can also be due to random failure of embedded sensor protocols. Thus, most wireless sensor applications, without tools to defend against rash battery exhausting, would be unable to function during prescribed times. In this paper, we consider a special type of threat, in which the harm is malicious depletion of sensor battery power. In contrast to the traditional denial-of-service attack, quality of service under the considered attack is not necessarily degraded. Moreover, the quality of service can increase up to the moment of the sensor set crashes. We argue that this is a distinguishing type of attack. Hence, the application of a traditional defense mechanism against this threat is not always possible. Therefore, effective methods should be developed to counter the threat. We first discuss the feasibility of rash depletion of battery power. Next, we propose a model for evaluation of energy consumption when under attack. Finally, a technique to counter the attack is discussed.
To receive location-based services (LBS), users must disclose their locations and queries to the LBS server, which can expose the user's identity, location, and other information. Recently, techniques for protecting user privacy using dummies have been researched. However, many factors, such as the distance between the obstacles and the dummies, must be considered in order to create dummies. Therefore, this study proposes an efficient dummy creation technique to improve user privacy protection. Experimental results show that the proposed technique improves on other recent techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.