Intelligent Blockchain security for smart cities: Artificial intelligence-based anomaly detection and data integrity

Blockchain is well known for its strong security features, but integrating it with Internet of Things systems introduces challenges related to scalability and operations. Incorporating Artificial Intelligence into blockchain environments raises concerns about maintaining strict security while ensuring computational efficiency. This paper proposes a novel security framework that integrates Artificial Intelligence systems with blockchain networks to detect anomalies and store data securely across multiple locations. The system gathers smart city data from different sources and then processes this information at Edge Layer facilities, where it determines quality and enhances data values for future investigation. The system moves verified data to the Ethereum Blockchain for protection against tampering and data alteration. Using a Refined Long Short-Term Graph Convolutional Network, the Cloud Layer performs sophisticated data analysis to monitor suspicious activity by recognizing interrelated temporal and spatial data patterns. Although the proposed approach offers higher security than normal systems through secure data confirmation and Artificial Intelligence threat-spotting functions, it has some important drawbacks. The smart city blockchain system faces scalability obstacles when processing many transactions because it needs excessive computing power and generates network traffic that it cannot handle. Additionally, the integration of Artificial Intelligence models introduces the risk of adversarial attacks, requiring continuous model updates and validation. Experimental results demonstrate the effectiveness of the Refined Long Short-Term Graph Convolutional Network model, with significant improvements in the accuracy of 98.98%, precision of 98.83%, and recall of 98.72% for detecting malicious activities. The framework combines Artificial Intelligence and Blockchain technology effectively to protect Internet of Things systems that support smart city functions.

Authors

Institutions

Publication Details

Journal
Peer-to-Peer Networking and Applications
Published
2026-02-16
DOI
https://doi.org/10.1007/s12083-025-02190-7
Primary Topic
Blockchain Technology Applications and Security
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Intelligent Blockchain security for smart cities: Artificial intelligence-based anomaly detection and data integrity

Palani Uthirapathy, Elavarasi Kumaran
Peer-to-Peer Networking and Applications
Blockchain Technology Applications and Security
article

Intelligent Blockchain security for smart cities: Artificial intelligence-based anomaly detection and data integrity

Palani Uthirapathy, Elavarasi Kumaran
article en

Abstract

Blockchain is well known for its strong security features, but integrating it with Internet of Things systems introduces challenges related to scalability and operations. Incorporating Artificial Intelligence into blockchain environments raises concerns about maintaining strict security while ensuring computational efficiency. This paper proposes a novel security framework that integrates Artificial Intelligence systems with blockchain networks to detect anomalies and store data securely across multiple locations. The system gathers smart city data from different sources and then processes this information at Edge Layer facilities, where it determines quality and enhances data values for future investigation. The system moves verified data to the Ethereum Blockchain for protection against tampering and data alteration. Using a Refined Long Short-Term Graph Convolutional Network, the Cloud Layer performs sophisticated data analysis to monitor suspicious activity by recognizing interrelated temporal and spatial data patterns. Although the proposed approach offers higher security than normal systems through secure data confirmation and Artificial Intelligence threat-spotting functions, it has some important drawbacks. The smart city blockchain system faces scalability obstacles when processing many transactions because it needs excessive computing power and generates network traffic that it cannot handle. Additionally, the integration of Artificial Intelligence models introduces the risk of adversarial attacks, requiring continuous model updates and validation. Experimental results demonstrate the effectiveness of the Refined Long Short-Term Graph Convolutional Network model, with significant improvements in the accuracy of 98.98%, precision of 98.83%, and recall of 98.72% for detecting malicious activities. The framework combines Artificial Intelligence and Blockchain technology effectively to protect Internet of Things systems that support smart city functions.

Peer-to-Peer Networking and ApplicationsVol. 19(2)
IFMR Graduate School of Business (IN)
Sustainable cities and communities
Openalex Percentile: Top 68%
Blockchain Technology Applications and Security
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Intelligent Blockchain security for smart cities: Artificial intelligence-based anomaly detection and data integrity — Palani Uthirapathy, Elavarasi Kumaran · Peer-to-Peer Networking and Applications (2026) | TGRS Research Map | TGRS