Blockchain transaction data mining and its applications

Since the birth of blockchain as the underlying support technology for Bitcoin, blockchain technology has received widespread attention from academia and industry worldwide and is considered to have profound potential for disruptive change in areas such as finance, smart manufacturing, and the Internet of Things. As cryptocurrencies, smart contracts, decentralized applications and other derivatives continue to be generated on the blockchain, the volume of transaction data on the blockchain has been maintaining a high growth. With the help of this massive data, we can dig out the development rules of the blockchain, analyze the characteristics of different transactions, and then identify the abnormal behaviour on the blockchain to promote the green and sustainable development of the blockchain. Unfortunately, blockchain transaction data mining faces challenges, such as blockchain data heterogeneity, anonymity and decentralization as well as real-time and generality.

This special issue aims to provide an open venue for academic and industrial communities to present and discuss cutting-edge technologies and research results regarding blockchain transaction data mining and its applications. It solicits original high-quality papers with new transaction data acquisition tools, transaction network construction and mining methods, anomaly detection algorithms, etc.

In this Special Issue, we have received eight papers, all of which underwent peer review. Of the eight originally submitted papers, five have been accepted. The overall submissions were of high quality, which marks the success of this Special Issue. A brief presentation of each of the paper in this special issue follows.

Xiong et al. introduce a graph neural network-based phishing detection method for Ethereum, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in identifying Ethereum phishing detection. The method introduces a feature learning algorithm named TransWalk and constructs an Ethereum phishing fraud detection framework utilizing a transaction-oriented biased sampling strategy for transaction networks and a multi-scale feature extraction method for Ethereum. Through more effective extraction of Ethereum transaction features, the framework aims to enhance phishing fraud detection performance. This work holds significant importance in the field of Ethereum ecosystem security. Access the full paper using the following link: https://doi.org/10.1049/blc2.12031.

Feng et al. propose a framework for detecting and repairing reentrancy vulnerabilities in smart contracts based on bytecode and vulnerability features. This framework aims to mitigate the losses incurred by reentrancy vulnerabilities in the digital currency economy and offers a more comprehensive solution for detecting and repairing such vulnerabilities. The proposed bytecode-level method overcomes challenges in detection and repair by integrating detection, auxiliary localization, and repair modules. Through extensive experimental validation, the effectiveness and superiority of the proposed methods are confirmed, further validating the feasibility of the entire framework. Experimental results demonstrate that the framework offers enhanced protection against reentrancy vulnerability attacks in smart contracts. Access the full paper using the following link: https://doi.org/10.1049/blc2.12043.

Sharma et al. analyze a pa Quantum-IoT-based data protection scheme that can be of value to Industry 4.0, named QIoTChain. By leveraging the principles of quantum key distribution, data encryption, and blockchain's decentralized and immutable nature, QIoTChain establishes a secure and trustworthy communication framework for IoT devices. This fusion provides robust protection against eavesdropping, tampering, and unauthorized access, ensuring the confidentiality, integrity, and authenticity of data in the industrial landscape. With periodic quantum key updates and regular security audits, QIoTChain continuously adapts to evolving threats, making it a reliable and future-proof solution for data protection in the Industry 4.0 era. Access the full paper using the following link: https://doi.org/10.1049/blc2.12059.

Tuma et al. study three major crypto communities in order to compare them, in a cost-benefit study logic. A cost-benefit analysis was performed between CURECOIN, BANANO, DOGECOIN folding, DOGECOIN mining and their communities on social platforms based on several outcomes: ‘Points Per Day (PPD)’, ‘Whattomine Mh/s Equivalent’, ‘Graphics Processing Units (GPU) Thermal Design Power/Typical Board Power Watts’, ‘Coins per 1,000,000 PPD’, ‘Coins per Day’, ‘Cost Per Coin’, ‘Cost Per Day’, ‘kWh Used Per Day’. Actually, BANANO, thanks to a large community and bots, has the highest PPD production and the lowest energetic cost on Central Processing Unit per week. On GPUs, DOGECOIN folding has the lowest weekly cost. However, the DOGECOIN community cannot produce as many PPD as the Banano team. CURECOIN offers a good compromise between the environmental point of view and the profitability one. Access the full paper using the following link: https://doi.org/10.1049/blc2.12060.

Gao et al. propose a Bitcoin service community classification method based on Random Forest and improved K-Nearest Neighbor (KNN) algorithm. First, the transaction characteristics of different types of communities are analyzed and summarized, and the corresponding transaction features are extracted from the address and entity levels; then multiple classification algorithms are compared, the optimal model to filter the effective features is selected, and the feature vector of entity addresses is constructed. Finally, a classification model is constructed based on Random Forest and improved KNN algorithm to classify the entities. By constructing different classification models for experimental comparison, the accuracy and stability advantages of the proposed method for classification in service community classification research are verified. Access the full paper using the following link: https://doi.org/10.1049/blc2.12064.

All of the papers selected for this Special Issue show that the field of blockchain transaction data mining and its applications is steadily moving forward. The possibility of uncovering novel insights and developing innovative solutions in blockchain transaction data mining and its applications will remain a source of inspiration for new techniques in the years to come.

The authors declare no conflict of interest.

Jiajing Wu received the B.Eng. degree in communication engineering from Beijing Jiaotong University, Beijing, China, in 2010, and the Ph.D. degree from Hong Kong Polytechnic University, Hong Kong, in 2014. She was awarded the Hong Kong Ph.D. Fellowship Scheme during her Ph.D. study in Hong Kong (2010–2014). She is currently an associate professor with the School of Software Engineering, Sun Yat-sen University, Zhuhai, China. Her research focus includes blockchain, graph mining, network science.

Hong-Ning Dai obtained his Ph.D. in computer science and engineering from the Department of Computer Science and Engineering at the Chinese University of Hong Kong. He is currently an associate professor in the Department of Computer Science, Hong Kong Baptist University, Hong Kong. His research interests include blockchain, the Internet of Things, and big data analytics. He has served as associate editor of IEEE Communications Surveys & Tutorials, IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Industrial Informatics, and IEEE Transactions on Industrial Cyber-Physical Systems. He is also a senior member of the Association for Computing Machinery.

Qi Xuan received the B.S. and Ph.D. degrees in control theory and engineering from Zhejiang University, Hangzhou, China, in 2003 and 2008, respectively. He was a postdoctoral researcher with the Department of Information Science and Electronic Engineering, Zhejiang University, from 2008 to 2010, and a research assistant with the Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China, in 2010 and 2017. From 2012 to 2014, he was a postdoctoral fellow with the Department of Computer Science, University of California at Davis, Davis, CA, USA. He is currently a professor with the Institute of Cyberspace Security, College of Information Engineering, Zhejiang University of Technology, Hangzhou, China. His current research interests include network science, graph data mining, deep learning, cyberspace security, machine learning, and computer vision.

Radosław Michalski is currently an associate professor with the Department of Artificial Intelligence, Wrocław University of Science and Technology, Wrocław, Poland. He co-leads the Network Science Laboratory and leads the Blockchain Exploration Research Group (BERG), both at Wrocław University of Science and Technology. His research interests include complex networks, distributed ledger technology, machine learning. He has coauthored more than 50 publications in these areas.

Xi Chen received the Ph.D. degree from the Hong Kong Polytechnic University, Hong Kong, SAR, China in 2009. He is the operation director of the Task Force of Power Industry Large Language Model Development, State Grid Smart Grid Research Institute, State Grid Corporation of China. He was the research director at State Grid US Representative Office, New York, NY, and the chief information officer at GEIRI North America, San Jose, CA. He was a postdoctoral research fellow at the Institute of Software, Chinese Academy of Science. He is the Chair-Elect of IEEE Power and Energy Circuits and Systems Technical Committee. He serves as editor of IEEE Transactions on Wireless Communications, and associate editor of IEEE Systems Journal, IEEE Open Journal of the Industrial Electronics Society, IET Blockchain etc. He is an IET Fellow and an IEEE Senior Member. His current research interests include the Internet of Things, smart grids, artificial intelligent applications and electric vehicle charging networks.