Collaborative Security Schemes for Wireless Sensor Networks

Sirajuddin, Mohammad; Kumar, B. Sateesh

doi:10.1007/978-981-16-7985-8_36

Cited by 3 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this model, the vector encoding function is estimated at first by using the following model: (8) Where, indicates the hidden layer, K is the encoding function, denotes the weight matrix, and is the bias value. Consequently, the cost function is estimated, which is defined as the distance function between the input and -30 36 reconstructed data.…”

Section: Deep Auto Neural Network (Dann) Based Classificationmentioning

confidence: 99%

See 1 more Smart Citation

An Intelligent Prairie Dog Optimization (IPDO) and Deep Auto-Neural Network (DANN) based IDS for WSN Security

et al. 2023

ijcsm

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) are targets of intrusion, which seeks to make these networks less capable of performing their duties or even completely eradicate them. The Intrusion Detection System (IDS) is highly important for WSN, since it aids in the identification and detection of harmful attacks that impair the network's regular functionality. In order to strengthen the security of WSN, several machine learning and deep learning approaches are employed in the traditional works. However, its main drawbacks are computational burden, system complexity, poor network performance outcomes, and high false alarms. Therefore, the goal of this study is to develop an intelligent IDS framework for significantly enhancing WSN security through the use of deep learning model. Here, the min-max normalization and data discretization operations are carried out to produce the preprocessed dataset. Then, an Intelligent Prairie Dog Optimization (IPDO) algorithm is used to reduce the dimensionality of features by identifying the best optimal solution with a higher convergence rate. Moreover, a Deep Auto-Neural Network (DANN) based classification method is used to properly forecast the class of data with less false alarms and higher detection rate. For evaluation, a thorough analysis is conducted to evaluate the performance and detection results of the proposed IPDO-DANN model.

show abstract

Section: Deep Auto Neural Network (Dann) Based Classificationmentioning

confidence: 99%

“…For evaluation, a thorough analysis is conducted to evaluate the performance and detection results of the proposed IPDO-DANN model. -30 31 reasons, including faulty hardware, software, node isolation, or environmental factors [7][8][9]. The WSNs' deployment in unsupervised situations raises the risk of attackers capturing nodes.…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Prairie Dog Optimization (IPDO) and Deep Auto-Neural Network (DANN) based IDS for WSN Security

et al. 2023

ijcsm

View full text Add to dashboard Cite

show abstract

“…Experimentation demonstrates that the proposed system effectively increases the probability of secure network routing paths while extending the network lifecycle. Among these, the black hole attack is one of the most severe threats to WSNs [3].…”

Section: Mitigation Of Black Hole and Selective Forwarding Attacks Th...mentioning

confidence: 99%

Mitigation of Black Hole and Selective Forwarding Attacks through Active Trust Mechanisms in Wireless Sensor Networks

Sirajuddin

Kumar

2023

IJSRCSEIT

View full text Add to dashboard Cite

In modern times, security remains a significant concern in wireless networks. Wireless sensor networks are widely employed in different practical situations. WSNs struggle with numerous internal and external threats, and detecting and defending against insider attacks is difficult. Insider attacks, in which intruders discard received data packets selectively, pose a significant risk to WSNs. The presence of black hole nodes within the network causes this issue. This research paper presents a secure and reliable route management methodology for WSNs that selects nodes and routing paths based on trust metrics. The proposed mechanism employs intelligent routing and node selection to defend against various types of assaults encountered during the routing process, including selective forwarding and black hole attacks. As a result, the paper identifies secure routes and establishes secure network routing. This scheme uses throughput, latency, and packet drop ratio as performance metrics. Experimentation demonstrates that the proposed system effectively increases the probability of secure network routing paths while extending the network lifecycle.

show abstract

“…The data preprocessor module uses discrete pre-processors to process the data and transform it into the appropriate form. The reaction module is in charge of setting off the alert if any intrusion is discovered, and the intrusion model is the database of previously known intrusion characteristics [2].…”

Section: A Intrusion Detection Systemmentioning

confidence: 99%

“…Because of their action, an alarm is sent. Machine learning-based intrusion detection systems (IDS) are used to identify and prevent security breaches in wireless sensor networks [2].…”

Section: B Use Of Machine Learning Techniques In Wsn Securitymentioning

confidence: 99%

Hybrid Intrusion Detection Method Based on Improved Adaboost and Enhanced SVM for Anomaly Detection in Wireless Sensor Networks

Sirajuddin¹

2022

ijarcs

View full text Add to dashboard Cite

The utilisation of Wireless Sensor Networks is quickly rising due to the fast progress of wireless sensor technologies. Due to limited resources, infrastructureless nature, and other factors, it faces major security difficulties. This study describes a hybrid IDS based on an improved AdaBoost and Enhanced SVM strategy for detecting network intrusions and monitoring node activity while classifying it as normal or abnormal. AdaBoost is used in combination with an SVM classifier to identify and classify intrusions. The suggested IDS considerably enhanced the network performance by recognising and eliminating malicious nodes from the network and avoiding DoS and sinkhole attacks. Results oproved that it performes better than other state of art methods in terms of transmission delay, detection rate, energy consumption, packet delivery rate. It also has the advantages of a simple structure and quick computation times.

show abstract

Collaborative Security Schemes for Wireless Sensor Networks

Cited by 3 publications

References 15 publications

An Intelligent Prairie Dog Optimization (IPDO) and Deep Auto-Neural Network (DANN) based IDS for WSN Security

An Intelligent Prairie Dog Optimization (IPDO) and Deep Auto-Neural Network (DANN) based IDS for WSN Security

Mitigation of Black Hole and Selective Forwarding Attacks through Active Trust Mechanisms in Wireless Sensor Networks

Hybrid Intrusion Detection Method Based on Improved Adaboost and Enhanced SVM for Anomaly Detection in Wireless Sensor Networks

Contact Info

Product

Resources

About