Summary The Internet of Things (IoT) has altered living by controlling devices/things over the Internet. IoT has specified many smart solutions for daily problems, transforming cyber‐physical systems (CPS) and other classical fields into smart regions. Most of the edge devices that make up the Internet of Things have very minimal processing power. To bring down the IoT network, attackers can utilize these devices to conduct a variety of network attacks. In addition, as more and more IoT devices are added, the potential for new and unknown threats grows exponentially. For this reason, an intelligent security framework for IoT networks must be developed that can identify such threats. In this paper, we have developed an unsupervised ensemble learning model that is able to detect new or unknown attacks in an IoT network from an unlabeled dataset. The system‐generated labeled dataset is used to train a deep learning model to detect IoT network attacks. Additionally, the research presents a feature selection mechanism for identifying the most relevant aspects in the dataset for detecting attacks. The study shows that the suggested model is able to identify the unlabeled IoT network datasets and DBN (Deep Belief Network) outperform the other models with a detection accuracy of 97.5% and a false alarm rate of 2.3% when trained using labeled dataset supplied by the proposed approach.
The interconnection of large number of smart devices and sensors for critical information gathering and analysis over the internet has given rise to the Internet of Things (IoT) network. In recent times, IoT has emerged as a prime field for solving diverse real-life problems by providing a smart and affordable solutions. The IoT network has various constraints like: limited computational capacity of sensors, heterogeneity of devices, limited energy resource and bandwidth etc. These constraints restrict the use of high-end security mechanisms, thus making these type of networks more vulnerable to various security attacks including malicious insider attacks. Also, it is very difficult to detect such malicious insiders in the network due to their unpredictable behaviour and the ubiquitous nature of IoT network makes the task more difficult. To solve such problems machine learning techniques can be used as they have the ability to learn the behaviour of the system and predict the particular anomaly in the system. So, in this paper we have discussed various security requirements and challenges in the IoT network. We have also applied various supervised machine learning techniques on available IoT dataset to deduce which among them is best suited to detect the malicious insider attacks in the IoT network.
Blockchain (BC) is a technology whose value today is estimated by the success of Bitcoin. However, the spectrum of Blockchain applications goes beyond the financial sector. It has displayed enormous potential for revamping the customary industry with its key merits like decentralization, persistency, anonymity, and auditability. In this paper we conduct a comprehensive survey on the blockchain technology, explaining its structure and functioning. This work has analyzed the potential of BC in seven crucial sectors vis. voting systems, supply chain management, the security of Internet of Things (IoT), healthcare, intelligent transportation systems, government services, and tourism. Moreover, this paper has critically evaluated the traditional technologies used in various sectors, the problems in them, and the benefits that will be provided by the employment of BC. With its future directions, this paper will help researchers to create and realize new value for various sectors that is beyond anything we can imagine with existing technologies.
MANET is a family of ad hoc networks that spans a huge spectrum of other networking paradigms such as WMN, WSN, and VANET etc. There is a dire need for strengthening the base of all these networks from the security point of view. The vulnerability of MANET towards the attacks is huge as compared to its wired counterparts. MANETs are vulnerable to attacks because of the unique characteristics which they exhibit like the absence of central authority, usage of wireless links, dynamism in topology, shared media, constrained resources, etc. The ramification being that the security needs of MANETs become absolutely different than the ones which exist in the customary networks. One of the basal vulnerabilities of MANETs comes from their peer to peer architecture which is completely open wherein the mobile nodes act as routers, the medium of communication is open making it reachable to both the legitimate users of the network as well as the malicious nodes. Consequently, there is a bankruptcy of clear line of defense from the perspective of security design. This in turn implies that any node which may even be authentic can enter the network and affect its performance by dropping the packets instead of forwarding them. The occurrences of the attacks of this type in ad hoc networks result in the situation where even the standard routing protocols do not provide the required security. The proposed solutions in literature such as SAODV, ARAN, and SEAODV all provide authentication and encryption based solutions to these attacks. But, the attack on availability which is the most common and easiest of them all cannot be avoided by the authentication and encryption because even the authentic user can be the attacker. Also, the encryption cannot be helpful to prevent such attacks. Therefore, in such a situation if a proper solution is not provided the entire MANET operation will get crippled. The main aim of this paper is to guarantee a security solution which provides defense against these attacks. To achieve this, a Multipath On-demand security Mechanism, called Secure Multipath Ad hoc On-demand Distance vector routing protocol (SMAODV), is presented which eliminates the malicious nodes from the network thereby preventing MANETs from the effects of such malicious nodes.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.