Intrusion Detection Model for Wireless Sensor Networks Based on MC-GRU

Jingjing, Zhou; Tongyu, Yang; Zhang, Jilin; Zhang, Guohao; Li, Xuefeng; Peng, Xiang

doi:10.1155/2022/2448010

Cited by 14 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The outcomes of a 5-Folds Cross Validation are presented in Table 5. In order to compare the performance of the proposed ML RF approach with DL based approaches, a pervious study proposed by Zhou et al 18 is used. Their study has been selected as it was the only study that we found…”

Section: Resultsmentioning

confidence: 99%

“…7. Comparing best performance results with a deep learning based intrusion detection approach from the literature 18 .…”

mentioning

confidence: 99%

“…The proximity between the two lines indicates the model's capability to generalize. A smaller gap suggests that the model is not excessively fitting the training data and exhibits competent generalization to unseen data.In order to compare the performance of the proposed ML RF approach with DL based approaches, a pervious study proposed by Zhou et al18 is used. Their study has been selected as it was the only study that we found…”

mentioning

confidence: 99%

See 2 more Smart Citations

A comparative analysis of using ensemble trees for botnet detection and classification in IoT

Saied,

Guirguis,

Madbouly

2023

Sci Rep

View full text Add to dashboard Cite

Enhancing IoT security is a corner stone for building trust in its technology and driving its growth. Limited resources and diversified nature of IoT devices make them vulnerable to attacks. Botnet attacks compromise the IoT systems and can pose significant security challenges. Numerous investigations have utilized machine learning and deep learning techniques to identify botnet attacks in IoT. However, achieving high detection accuracy with reasonable computational requirements is still a challenging research considering the particularity of IoT. This paper aims to analytically study the performance of the tree based machine learning in detecting botnet attacks for IoT ecosystems. Through an empirical study performed on a public botnet dataset of IoT environment, basic decision tree algorithm in addition to ensemble learning of different bagging and boosting algorithms are compared. The comparison covers two perspectives: IoT botnet detection capability and computational performance. Results demonstrated that the significant potential for the tree based ML algorithms in detecting network intrusions in IoT environments. The RF algorithm achieved the best performance for multi-class classification with accuracy rate of 0.999991. It achieved also the highest results in all other measures.

show abstract

Section: Resultsmentioning

confidence: 99%

“…7. Comparing best performance results with a deep learning based intrusion detection approach from the literature 18 .…”

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A comparative analysis of using ensemble trees for botnet detection and classification in IoT

Saied,

Guirguis,

Madbouly

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Jingjing et al 27 provided an MCGRU WSN intrusion detection model centered on convolutional neural networks (CNN) along with gated recurrent units (GRU), which resolved the problems of lower detection accuracy as well as deprived real‐time detection. The experiment outcomes centered on the WSN‐DS dataset exhibited that the whole detection accuracy of the different kinds of attack of an black hole, gray hole, flooding, along with scheduling and normal behaviors attained 99.57%.…”

Section: Related Workmentioning

confidence: 99%

An accurate attack detection framework based on exponential polynomial kernel‐centered deep neural networks in the wireless sensor network

Bokka

Sadasivam

2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

A novel type of wireless network that is rising in popularity with a wide assortment of civilian along with military applications is called WSN. Owing to several factors like nodes with resources that are constrained and packages that are resistant to tamper, WSNs are tremendously vulnerable to internal attacks and mainly external attacks also. Attacks on such critical schemes comprise penetrations into their network along with the installation of malicious tools or programs, which can reveal sensitive data or alter the specific physical equipment's behavior. For their action, the wireless networks are utilized by the threats like spoofing, injection, denial of services, and numerous attacks. Thus, for protecting devices from intruder attacks, security solutions are necessary. An intrusion detection system (IDS), which is wielded for detecting attacks against a system or a network by evaluating their activities along with events, is a tool. In this article, an efficient attack detection technique grounded on exponential polynomial kernel-centered deep neural networks (EPK-DNN) is proposed since intrusion detection is crucial in securing the data. Intrusion detection in WSN is extremely intricate for tasks like fault diagnosis, and real-time monitoring applications, owing to the WSN's dynamicity. To find diverse attacks along with to safeguard WSNs from security risks, numerous detection methodologies are created, because intrusion detection is decisive for protecting the data in WSNs. However, owing to the restricted resources and energy of WSN nodes, widespread computation and so forth, they are inefficient. In this article, an efficient attack detection methodology centered on EPK-DNN is proposed to lessen these problems. The attack detection system's training is the foremost step in the EPK-DNN technique. In step one, the input data are preprocessed; and then, in the training process, the preprocessed data are exploited for attribute extraction. In step two, by utilizing the linear scaling based BAT optimization (LS-BAT), the major attributes are chosen. Then, to detect attacks in WSN, the chosen features are trained by the EPK-DNN. In step three, by utilizing the Damerau-Levenshtein-based K-means algorithm (DL-K-Means), the WSN network is initialized along with the sensor nodes are clustered. To amass the sensor data, the cluster heads are selected by utilizing the swap, displacement, and reversion-centered rock hyraxes swarm optimization algorithm. After that, for

show abstract

“…In WSN, intrusion detection is imperative due to high data transfer. To address low accuracy resulting from attacks in WSN, the Multiple Convolutional and Gated Recurrent Unit (MC-GRU) method is employed ( Jingjing et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Connect attack in IoT-WSN detect through cyclic analysis based on forward and backward elimination

S.,

2024

PeerJ Computer Science

View full text Add to dashboard Cite

IoT-wireless sensor networks (WSN) have extensive applications in diverse fields such as battlegrounds, commercial sectors, habitat monitoring, buildings, smart homes, and traffic surveillance. WSNs are susceptible to various types of attacks, such as malicious attacks, false data injection attacks, traffic attacks, and HTTP flood attacks. CONNECT attack is a novel attack in WSN. CONNECT attack plays a crucial role through disrupting packet transmission and node connections and significantly impacts CPU performance. Detecting and preventing CONNECT attacks is imperative for enhancing WSN efficiency. During a CONNECT attack, nodes fail to respond to legitimate requests, resulting in connectivity delays, acknowledgment delays, and packet drop attacks in IoT-WSN nodes. This article introduces an Intrusion Detection Algorithm based on the Cyclic Analysis Method (CAM), which incorporates a forward selection approach and backward elimination method. CAM analyzes routing information and behavior within the WSN, facilitating the identification of malicious paths and nodes. The proposed approach aims to pinpoint and mitigate the risks associated with CONNECT attacks, emphasizing the identification of malevolent pathways and nodes while establishing multiple disjoint loop-free routes for seamless data delivery in the IoT-WSN. Furthermore, the performance of CAM is assessed based on metrics such as malicious node detection accuracy, connectivity, packet loss, and network traffic. Simulation results using Matlab software demonstrate superior accuracy in malicious node detection, achieving accuracy in attack detection of approximately 99%, surpassing traditional algorithms accuracy of attack detection.

show abstract

Intrusion Detection Model for Wireless Sensor Networks Based on MC-GRU

Cited by 14 publications

References 15 publications

A comparative analysis of using ensemble trees for botnet detection and classification in IoT

A comparative analysis of using ensemble trees for botnet detection and classification in IoT

An accurate attack detection framework based on exponential polynomial kernel‐centered deep neural networks in the wireless sensor network

Connect attack in IoT-WSN detect through cyclic analysis based on forward and backward elimination

Contact Info

Product

Resources

About