Blockchain-Enhanced Security for 5G Edge Computing in IoT DOI Creative Commons
Manuel J. C. S. Reis

Computation, Journal Year: 2025, Volume and Issue: 13(4), P. 98 - 98

Published: April 18, 2025

The rapid expansion of 5G networks and edge computing has amplified security challenges in Internet Things (IoT) environments, including unauthorized access, data tampering, DDoS attacks. This paper introduces EdgeChainGuard, a hybrid blockchain-based authentication framework designed to secure 5G-enabled IoT systems through decentralized identity management, smart contract-based access control, AI-driven anomaly detection. By combining permissioned permissionless blockchain layers with Layer-2 scaling solutions adaptive consensus mechanisms, the enhances both scalability while maintaining computational efficiency. Using synthetic datasets that simulate real-world adversarial behaviour, our evaluation shows an average latency 172.50 s 50% reduction gas fees compared traditional Ethereum-based implementations. results demonstrate EdgeChainGuard effectively enforces tamper-resistant authentication, reduces adapts dynamic network conditions. Future research will focus on integrating zero-knowledge proofs (ZKPs) for privacy preservation, federated learning AI retraining, lightweight detection models enable secure, low-latency resource-constrained deployments.

Language: Английский

Federated Subgraph Learning via Global-Knowledge-Guided Node Generation DOI Creative Commons

Yuxuan Liu,

Zhiming He,

Shuang Wang

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(7), P. 2240 - 2240

Published: April 2, 2025

Federated graph learning (FGL) is a combination of representation and federated that utilizes neural networks (GNNs) to process complex graph-structured data while addressing silo issues. However, during the local training GNNs, each client only has access subgraph, significantly deteriorating performance. To address this issue, recent solutions propose completing subgraph with pseudo nodes generated by generator trained using subgraph. Despite their effectiveness, such methods may introduce biases as cannot accurately represent global distribution. overcome problem, we MN-FGAGN, which mitigates impact missing neighbor information generating follow The main idea our approach partition generative adversarial network into client-side discriminator server-side generator. In way, can receive supervised from all clients thus generate contain information. Experiments on four real-world datasets show it outperforms state-of-the-art methods.

Language: Английский

Citations

0
Blockchain-Enhanced Security for 5G Edge Computing in IoT DOI Creative Commons
Manuel J. C. S. Reis

Computation, Journal Year: 2025, Volume and Issue: 13(4), P. 98 - 98

Published: April 18, 2025

The rapid expansion of 5G networks and edge computing has amplified security challenges in Internet Things (IoT) environments, including unauthorized access, data tampering, DDoS attacks. This paper introduces EdgeChainGuard, a hybrid blockchain-based authentication framework designed to secure 5G-enabled IoT systems through decentralized identity management, smart contract-based access control, AI-driven anomaly detection. By combining permissioned permissionless blockchain layers with Layer-2 scaling solutions adaptive consensus mechanisms, the enhances both scalability while maintaining computational efficiency. Using synthetic datasets that simulate real-world adversarial behaviour, our evaluation shows an average latency 172.50 s 50% reduction gas fees compared traditional Ethereum-based implementations. results demonstrate EdgeChainGuard effectively enforces tamper-resistant authentication, reduces adapts dynamic network conditions. Future research will focus on integrating zero-knowledge proofs (ZKPs) for privacy preservation, federated learning AI retraining, lightweight detection models enable secure, low-latency resource-constrained deployments.

Language: Английский

Citations

0