“…Meanwhile, in the specification-based method, malicious behavior is detected through the behavior deviation of system from the expertdefined rules [23]. You et al [10] and Sharma et al [11] applied behavior-rules specification-based approach for misbehavior detection in healthcare IoT and UAV-IoT, respectively. The authors derived the behavior-rules from a given operation profile.…”
Section: Related Workmentioning
confidence: 99%
“…This section presents the derivation of the behavior-rule of the sample smart greenhouse environment. The steps adopted in the derivation of behavior-rules are inspired by [11].…”
Section: Behavior-rule Specification Of Smart Greenhouse Farmmentioning
confidence: 99%
“…Accordingly, this paper proposes a distributed behavior-rule specification-based misbehavior detection approach to detect misbehaving sensing nodes in SGF. Related work in [10] and [11] derived behaviorrules to monitor a target node. However, the rules were derived from the assumption that the monitoring nodes have the same sensing capabilities and access to the same phenomenon.…”
Smart farming is rapidly revolutionizing the agricultural sector where embedded Internet of Things (IoT) devices are integrated into the field to maintain or improve the quality of products as well as increase food production. Despite the tremendous benefits, various cybersecurity threats of IoT can also be inherited by the sector. In this paper, we propose a lightweight specification-based distributed detection to identify the misbehavior of heterogeneous embedded IoT nodes efficiently and effectively in a closed-loop smart greenhouse farming system. To expand the monitoring space of a node, we exploited the Kalman-filter algorithm and simple statistical operations to obtain estimates of data. Accordingly, this enables a monitoring node to assess a target node that has distinct physical characteristics and access to natural phenomena. Along with this, we derive the behavior-rules that are specific to the target system and carefully translate these rules into a state machine diagram. Besides, we formally verify the functional correctness of the monitoring processes as well as ensure that the behavior specifications are completely covered by using the model checker tool UPPAAL. Through extensive experimental simulation using Proteus, we verify its applicability to resource-constrained embedded devices, e.g., Arduino-Uno, as well as show high accuracy in detecting misbehaving nodes while having low false alarms.
“…Meanwhile, in the specification-based method, malicious behavior is detected through the behavior deviation of system from the expertdefined rules [23]. You et al [10] and Sharma et al [11] applied behavior-rules specification-based approach for misbehavior detection in healthcare IoT and UAV-IoT, respectively. The authors derived the behavior-rules from a given operation profile.…”
Section: Related Workmentioning
confidence: 99%
“…This section presents the derivation of the behavior-rule of the sample smart greenhouse environment. The steps adopted in the derivation of behavior-rules are inspired by [11].…”
Section: Behavior-rule Specification Of Smart Greenhouse Farmmentioning
confidence: 99%
“…Accordingly, this paper proposes a distributed behavior-rule specification-based misbehavior detection approach to detect misbehaving sensing nodes in SGF. Related work in [10] and [11] derived behaviorrules to monitor a target node. However, the rules were derived from the assumption that the monitoring nodes have the same sensing capabilities and access to the same phenomenon.…”
Smart farming is rapidly revolutionizing the agricultural sector where embedded Internet of Things (IoT) devices are integrated into the field to maintain or improve the quality of products as well as increase food production. Despite the tremendous benefits, various cybersecurity threats of IoT can also be inherited by the sector. In this paper, we propose a lightweight specification-based distributed detection to identify the misbehavior of heterogeneous embedded IoT nodes efficiently and effectively in a closed-loop smart greenhouse farming system. To expand the monitoring space of a node, we exploited the Kalman-filter algorithm and simple statistical operations to obtain estimates of data. Accordingly, this enables a monitoring node to assess a target node that has distinct physical characteristics and access to natural phenomena. Along with this, we derive the behavior-rules that are specific to the target system and carefully translate these rules into a state machine diagram. Besides, we formally verify the functional correctness of the monitoring processes as well as ensure that the behavior specifications are completely covered by using the model checker tool UPPAAL. Through extensive experimental simulation using Proteus, we verify its applicability to resource-constrained embedded devices, e.g., Arduino-Uno, as well as show high accuracy in detecting misbehaving nodes while having low false alarms.
“…Das et al [26] used EllipticCurve Cryptography and key-agreement techniques to design a lightweight security mechanism for the IoT system. Sharma et al [27] utilize the approach of behavior rule specification to design a misbehavior recognition scheme for a cyber-based IoT ecosystem. Dynamic characteristics obtained from creeping wave propagation is utilized in the study Wang et al [28] to provide safeguard to on-body IoT devices.…”
Internet-of-Things (IoT) is an inevitable domain of technology that is going to capture the connectivity of the majority of the smart devices in the coming days supported by huge advancement in mobile computing. However, IoT still suffers serious security issues when it comes to performing extensive communication over a broad range of heterogeneous devices. A review of existing secure routing schemes shows that they are complex in operation overlooking the communication performance and resource-constrained factors. Therefore, the proposed system introduces a very novel, simple, and cost-effective, secure routing scheme that is not only capable of identifying the threats without any apriority information of adversary, but they are equally capable of isolating the threats from the connectivity of regular IoT nodes. The simulated outcome of the proposed system shows that it offers a better solution towards security in contrast to existing security approaches frequently exercised in IoT at present
“…IDS detects whether there is an attack behavior in the network and immediately performs response processing. Recently, a large number of techniques are applied to intrusion detection, such as rule-based network intrusion detection technology [8], artificial immune system [9], clustering-based technology [10,11], Support Vector Machine (SVM) [12,13], neural network [14][15][16], etc. Currently, among many intrusion detection algorithms, neural network-related algorithms have been widely used because of their good robustness and adaptability.…”
The Internet of Things (IoT) is widely applied in modern human life, e.g., smart home and intelligent transportation. However, it is vulnerable to malicious attacks, and the current existing security mechanisms cannot completely protect the IoT. As a security technology, intrusion detection can defend IoT devices from most malicious attacks. However, unfortunately the traditional intrusion detection models have defects in terms of time efficiency and detection efficiency. Therefore, in this paper, we propose an improved linear discriminant analysis (LDA)-based extreme learning machine (ELM) classification for the intrusion detection algorithm (ILECA). First, we improve the linear discriminant analysis (LDA) and then use it to reduce the feature dimensions. Moreover, we use a single hidden layer neural network extreme learning machine (ELM) algorithm to classify the dimensionality-reduced data. Considering the high requirement of IoT devices for detection efficiency, our scheme not only ensures the accuracy of intrusion detection, but also improves the execution efficiency, which can quickly identify the intrusion. Finally, we conduct experiments on the NSL-KDD dataset. The evaluation results show that the proposed ILECA has good generalization and real-time characteristics, and the detection accuracy is up to 92.35%, which is better than other typical algorithms.
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.