Malicious Node Detection Using Machine Learning and Distributed Data Storage Using Blockchain in WSNs

Abstract

In the proposed work, blockchain is implemented on the Base Stations (BSs) and Cluster Heads (CHs) to register the nodes using their credentials and also to tackle various security issues. Moreover, a Machine Learning (ML) classifier, termed as Histogram Gradient Boost (HGB), is employed on the BSs to classify the nodes as malicious or legitimate. In case, the node is found to be malicious, its registration is revoked from the network. Whereas, if a node is found to be legitimate, then its data is stored in an Interplanetary File System (IPFS). IPFS stores the data in the form of chunks and generates hash for the data, which is then stored in blockchain. In addition, Verifiable Byzantine Fault Tolerance (VBFT) is used instead of Proof of Work (PoW) to perform consensus and validate transactions. Also, extensive simulations are performed using the Wireless Sensor Network (WSN) dataset, referred as WSN-DS. The proposed model is evaluated both on the original dataset and the balanced dataset. Furthermore, HGB is compared with other existing classifiers, Adaptive Boost (AdaBoost), Gradient Boost (GB), Linear Discriminant Analysis (LDA), Extreme Gradient Boost (XGB) and ridge, using different performance metrics like accuracy, precision, recall, micro-F1 score and macro-F1 score. The performance evaluation of HGB shows that it outperforms GB, AdaBoost, LDA, XGB and Ridge by 2-4%, 8-10%, 12-14%, 3-5% and 14-16%, respectively. Moreover, the results with balanced dataset are better than those with original dataset. Also, VBFT performs 20-30% better than PoW. Overall, the proposed model performs efficiently in terms of malicious node detection and secure data storage.

Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam

“…This algorithm is an extension of the well-known Ridge regression technique used for regression tasks, and it brings the benefits of regularization to the realm of classification. At its core, the Ridge classifier is a linear classification model (Nouman et al 2023). It operates by establishing a linear decision boundary within the feature space to distinguish between different classes.…”

Digital Incontrovertible Multi Level Key Set Based Node Authentication Model for Malicious Node Detection for Secure Data Transmission in WSN

“…In order to manage node registration with credentials and other security issues, Nouman et al [9] presented a concept in which blockchain is implemented on the BSs and CHs. Histogram Gradient Boost (HGB) is a Machine Learning (ML) classifier used by the BSs to detect if the nodes in question are malicious.…”

“…activities within WSNs, these networks remain susceptible to an array of security threats and weaknesses [9]. It has been observed that nodes which act selfishly or maliciously, contravening the established protocol norms, can disrupt the routing process.…”

“…It has been observed that nodes which act selfishly or maliciously, contravening the established protocol norms, can disrupt the routing process. WSN attacks can be categorized broadly into internal and external types [9]. External attacks often target authentication and key management systems [10], and although cryptographic measures, authorization, and encryption are employed to counter these threats, their efficacy is compromised in the face of internal attacks.…”

Supervised Machine Learning Framework for Deanonymization of Transactional Entities in Decentralized Infrastructure Environment

“…This research seeks to offer an enhanced comprehension of the diverse Bitcoin transactions in order to more effectively educate administrative and institutional factors connected to regulatory and compliance with laws. We achieve this by utilizing supervised machine learning's potential to de-anonymize the Bitcoin ecosystem in order to assist in the identification of high-risk counterparties and likely cybercriminal activities [10]. Legal constraints (such as those related to safeguarding against money laundering protocols) or reputational risk considerations may result in adverse outcomes for organizations when they communicate with counterparties who pose a high risk on the Bitcoin network.…”