Resource Management and Secure Data Exchange for Mobile Sensors Using Ethereum Blockchain

Symmetry, Journal Year: 2025, Volume and Issue: 17(1), P. 61 - 61

Published: Jan. 1, 2025

A typical Wireless Sensor Network (WSN) defines the usage of static sensors; however, growing focus on smart cities has led to a rise in adoption mobile sensors meet varied demands Internet Things (IoT) applications. This results significantly increasing dependencies towards secure storage and effective resource management. One way address this issue is harness immutability property Ethereum blockchain. However, existing challenges IoT communication using blockchain are noted eventually lead symmetry issues network dynamics Ethereum. The key related scalability, disparities, centralization risk, which offer sub-optimal opportunities for nodes gain benefits, influence, or participate processes network. Therefore, paper presents novel blockchain-based computation model optimizing utilization offering data exchange during active among sensors. An empirical method trust was carried out identify degree legitimacy sensor participation Finally, cost been presented estimation enhance users’ quality experience. With aid simulation study, benchmarked outcome study exhibited that proposed scheme achieved 40% reduced validation time, 28% latency, 23% improved throughput, 38% minimized overhead, 27% cost, processing contrast solutions reported literature. prominently exhibits fairer system.

Language: Английский

---

A Novel Deep Federated Learning-Based Model to Enhance Privacy in Critical Infrastructure Systems

International Journal of Software Science and Computational Intelligence, Journal Year: 2023, Volume and Issue: 15(1), P. 1 - 23

Published: Dec. 15, 2023

Deep learning (DL) can provide critical infrastructure operators with valuable insights and predictive capabilities to help them make more informed decisions, improving system's robustness. However, training DL models requires large amounts of data, which be costly store in a centralized manner. Storing sensitive data the cloud pose significant security risks. Federated (FL) allows several clients share train ML models. Unlike models, FL does not require sharing client data. A novel framework is presented VGG16 based CNN global model without only updating local among using federated averaging. For experimentation, MNIST dataset used. The achieves high accuracy keep private infrastructures. benefits challenges along vulnerabilities attacks have been discussed defenses that used mitigate these attacks.

Language: Английский

---

Proactive Threat Hunting in Critical Infrastructure Protection through Hybrid Machine Learning Algorithm Application

Sensors, Journal Year: 2024, Volume and Issue: 24(15), P. 4888 - 4888

Published: July 27, 2024

Cyber-security challenges are growing globally and specifically targeting critical infrastructure. Conventional countermeasure practices insufficient to provide proactive threat hunting. In this study, random forest (RF), support vector machine (SVM), multi-layer perceptron (MLP), AdaBoost, hybrid models were applied for By automating detection, the learning-based method improves hunting frees up time concentrate on high-risk warnings. These implemented approach devices, access, principal servers. The efficacy of several models, including approaches, is assessed. findings these studies that AdaBoost model provides highest efficiency, with a 0.98 ROC area 95.7% accuracy, detecting 146 threats 29 false positives. Similarly, achieved under curve 95% overall accurately identifying 132 reducing positives 31. exhibited promise 0.89 94.9% though it requires further refinement lower its positive rate. This research emphasizes role learning in improving cyber-security, particularly Advanced ML techniques enhance detection response times, their continuous ability ensures adaptability new threats.

Language: Английский

---

Dynamic Optimization for Trade-off in Hyperledger Fabric towards Latency-Sensitive IoT Services

Published: July 7, 2024

Language: Английский

---

A novel approach for end-to-end navigation for real mobile robots using a deep hybrid model

Intelligent Service Robotics, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 21, 2024

Language: Английский

---