Wireless sensor network intrusion detection system based on MK-ELM

Zhang, Wenjie; Han, Dong‐Guk; Li, Kuan‐Ching; Massetto, Francisco Isidro

doi:10.1007/s00500-020-04678-1

Cited by 76 publications

(26 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of SVM is to find the optimal level of separation between two categories by maximizing the margin between the closest points to the categories. However, the SVM has many drawbacks such as high computations for train data, sensitive to noisy data, and unbalanced data sets [18]. Therefore, due to the size of D1 and D2, the SVM was not working and we did not get any results.…”

Section: Resultsmentioning

confidence: 92%

“…The authors in [1,2,[13][14][15][16][17] used different techniques related to deep learning mechanism, and their results regarding to detection accuracy, mean squared error, and sensitivity showed good performance, but none of them discussed the effect of their proposal on WSN networks such as nodes power consumption and network lifetime. Moreover, other publications were using regular networks traffic datasets instead of WSN nodes datasets [18]. Other algorithms for detecting DDoS have been proposed in [19], the work used authentication policy to remove DoS attacks by splitting the WSN nodes into clusters and linking all cluster WSN nodes in a single authentication message.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approaches to Detect DoS and Their Effect on WSNs Lifetime

Wazirali¹,

Ahmad²

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Energy and security remain the main two challenges in Wireless Sensor Networks (WSNs). Therefore, protecting these WSN networks from Denial of Service (DoS) and Distributed DoS (DDoS) is one of the WSN networks security tasks. Traditional packet deep scan systems that rely on open field inspection in transport layer security packets and the open field encryption trend are making machine learning-based systems the only viable choice for these types of attacks. This paper contributes to the evaluation of the use machine learning algorithms in WSN nodes traffic and their effect on WSN network life time. We examined the performance metrics of different machine learning classification categories such as K-Nearest Neighbour (KNN), Logistic Regression (LR), Support Vector Machine (SVM), Gboost, Decision Tree (DT), Naïve Bayes, Long Short Term Memory (LSTM), and Multi-Layer Perceptron (MLP) on a WSN-dataset in different sizes. The test results proved that the statistical and logical classification categories performed the best on numeric statistical datasets, and the Gboost algorithm showed the best performance compared to different algorithms on average of all performance metrics. The performance metrics used in these validations were accuracy, F1-score, False Positive Ratio (FPR), False Negative Ratio (FNR), and the training execution time. Moreover, the test results showed the Gboost algorithm got 99.6%, 98.8%, 0.4% 0.13% in accuracy, F1-score, FPR, and FNR, respectively. At training execution time, it obtained 1.41 s for the average of all training time execution datasets. In addition, this paper demonstrated that for the numeric statistical data type, the best results are in the size of the dataset ranging from 3000 to 6000 records and the percentage between categories is not less than 50% for each category with the other categories. Furthermore, this paper investigated the effect of Gboost on the WSN lifetime, which resulted in a 32% reduction compared to other Gboost-free scenarios.

show abstract

Section: Resultsmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Machine Learning Approaches to Detect DoS and Their Effect on WSNs Lifetime

Wazirali¹,

Ahmad²

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…In recent years, many methods have been proposed to detect intrusions or anomalies in wireless sensor networks [16]- [18]. The data clustering method is usually used to detect irregular nodes, and game theory is often used to design the most profitable scheme for common nodes based on the behavior features of suspicious nodes.…”

Section: Related Workmentioning

confidence: 99%

Combine Clustering With Game to Resist Selective Forwarding in Wireless Sensor Networks

2020

IEEE Access

View full text Add to dashboard Cite

Deployed in a harsh or hostile environment and running in an unattended state, wireless sensor networks (WSNs) are vulnerable to many attacks. The selective forwarding attack is one most difficult to be detected, and trust-based detection methods often fail especially under the poor wireless channels. Based on nodes' cumulative forwarding rates (CFRs) and cumulative transmission rates (CTRs), we propose a clustering scheme in clustered WSNs to divide the nodes into three types: malicious, suspicious, and regular nodes. To defend selective forwarding attacks of malicious nodes, our scheme isolates them from the network. For suspicious nodes, our scheme uses the non-cooperative game with incomplete information to force them to promote forwarding rates. In the game, the reward and punishment mechanism reduces the attackers' expected revenues and trust values. And the suspicious nodes, screened out by our clustering method, will be forced to forward packets to elude our detecting scheme. The Nash equilibrium of the game between regular nodes and suspicious nodes is proved to exist here. Simulation results show that our scheme can promote network throughput largely, and our dynamic-time behavior monitoring scheme can gain a longer network lifetime than that of the full-time behavior monitoring scheme.INDEX TERMS Cluster-based wireless sensor networks, density-based clustering, game theory, network throughput, Nash equilibrium, selective forwarding attack.

show abstract

“…The second type is the cluster-based network and the third type is the hierarchical network. The routing of packets is the most challenging task in wireless sensor networks (WSN) [2]. The data packets are transmitted from the individual sensor node to the cluster head node and are then transmitted to the base station.…”

Section: Introductionmentioning

confidence: 99%

Detection and Avoidance of Clone Attack in IoT Based Smart Health Application

Vaishnavi¹,

Sethukarasi²

2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

The deployment of wireless sensors in the hostile environment makes them susceptible to malicious attacks. One of the most harmful attacks is the clone attack in which a malicious node illegitimately claims the identity of a genuine node in the network and eventually tries to capture the entire network. This attack is also termed as node replication attack. The mobile nature of wireless sensor network (WSN) in smart health environment increases the vulnerability of node replication attack. Since the data involved in smart health system are highly sensitive data, preserving the system from the attack by malicious nodes is a crucial task. In this research, we proposed a new scheme called Routing Protocol for Energy Efficient Networks (RPEEN) for the detection of clone attack in IoT-based smart health application. The main advantage of this scheme is the increase in the energy efficiency as the energy efficiency is the most important constraint in WSN systems. The performance of the proposed scheme is highlighted using parameters like time delay, residual energy, throughput, energy efficiency and error rate. Further, to portray the efficacy of the proposed algorithm, this algorithm is compared with the existing Hybrid Multi-Level Clustering (HMLC) algorithm. It has been found that the proposed RPEEN scheme achieves a time delay of 0.63 and 0.6 ms with 0 dead nodes and by avoiding clone attack respectively. Furthermore, the proposed scheme attains the highest residual energy of 49.5 J for the 2500 rounds. In addition, the proposed algorithm attains the highest throughput of 99.2% for the 50 nodes.

show abstract

Wireless sensor network intrusion detection system based on MK-ELM

Cited by 76 publications

References 16 publications

Machine Learning Approaches to Detect DoS and Their Effect on WSNs Lifetime

Machine Learning Approaches to Detect DoS and Their Effect on WSNs Lifetime

Combine Clustering With Game to Resist Selective Forwarding in Wireless Sensor Networks

Detection and Avoidance of Clone Attack in IoT Based Smart Health Application

Contact Info

Product

Resources

About