[1]ZHANG Mingquan,JIA Wenli,MENG Limin,et al.A blockchain abnormal transaction detection method integrating graph enhancement and multi-teacher dynamic distillation[J].CAAI transactions on intelligent systems,2026,21(5):1154-1165.[doi:10.11992/tis.202510002]
Copy

A blockchain abnormal transaction detection method integrating graph enhancement and multi-teacher dynamic distillation

CAAI transactions on intelligent systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 5 Page number: 1154-1165 Column: 学术论文—机器学习 Public date: 2026-09-05
Title:
A blockchain abnormal transaction detection method integrating graph enhancement and multi-teacher dynamic distillation
Author(s):
ZHANG Mingquan1; 2;  JIA Wenli1;  MENG Limin3;  ZHAO Junxian1
1. School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China;
2. Engineering Research Center of Intelligent Computing for Complex Energy Systems, Ministry of Education, North China Electric Power University, Baoding 071003, China;
3. Network and Information Office, North China Electric Power University, Baoding 071003, China
Keywords:
blockchain; anomaly detection; graph neural network; dnowledge distillation; SMOTE; multi-teacher model; dynamic distillation; feature enhancement
CLC:
TP309；TP18
DOI:
10.11992/tis.202510002
Abstract:
To address the limitations of existing blockchain abnormal transaction detection methods in complex transaction structure modeling and data imbalance handling, this paper proposes a detection method called MGDD (multi-teacher GNN dynamic distillation) that integrates graph neural network teacher models, motif structural features, SMOTE sampling, and multi-student model knowledge distillation. This method first enhances node structural representation using motif statistics, then constructs multiple teacher models by combining GCN, GAT, GIN, and GraphSAGE graph neural networks. Through a dynamic distillation mechanism, it guides multi-layer perceptron (MLP) and random forest (RF) student models to learn high-order semantic features from graphs, and introduces SMOTE for oversampling to alleviate the sample imbalance problem. Experimental results on the Elliptic dataset demonstrate that MGDD outperforms existing typical methods in terms of accuracy, recall rate, and F1-score, with the RF student model achieving an accuracy rate of 99.23% under the guidance of distillation. Ablation and robustness experiments further verify the important role of motif features and knowledge distillation mechanisms in improving detection performance and model stability. In summary, MGDD provides an efficient and scalable modeling paradigm for blockchain abnormal transaction detection tasks, showing promising application prospects.
References:
[1] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. (2016-09-09)[2025-10-08]. https://arxiv.org/abs/1609.02907.
[2] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. (2017-10-30)[2025-10-08]. https://arxiv.org/abs/1710.10903.
[3] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[EB/OL]. (2017-06-07)[2025-10-08]. https://arxiv.org/abs/1706.02216.
[4] WEBER M, DOMENICONI G, CHEN Jie, et al. Anti-money laundering in Bitcoin: experimenting with graph convolutional networks for financial forensics[EB/OL]. (2019-08-31)[2025-10-08]. https://arxiv.org/abs/1908.02591.
[5] JULLUM M, L?LAND A, HUSEBY R B, et al. Detecting money laundering transactions with machine learning[J]. Journal of money laundering control, 2020, 23(1): 173-186
[6] PINNA A, TONELLI R, ORR? M, et al. A Petri nets model for blockchain analysis[J]. The computer journal, 2018, 61(9): 1374-1388
[7] ANDROULAKI E, KARAME G O, ROESCHLIN M, et al. Evaluating user privacy in bitcoin[C]//International Conference on Financial Cryptography and Data Security. Berlin: Springer Berlin Heidelberg, 2013: 34-51.
[8] FARRUGIA S, ELLUL J, AZZOPARDI G. Detection of illicit accounts over the Ethereum blockchain[J]. Expert systems with applications, 2020, 150: 113318
[9] IBRAHIM R F, MOHAMMAD ELIAN A, ABABNEH M. Illicit account detection in the ethereum blockchain using machine learning[C]//2021 International Conference on Information Technology. Amman: IEEE, 2021: 488-493.
[10] 王栋, 李达, 王合建. 基于深度PCA与贝叶斯优化的区块链异常交易检测[J]. 南方电网技术, 2024, 18(9): 78-87, 105 WANG Dong, LI Da, WANG Hejian. Blockchain abnormal transaction detection based on deep PCA and Bayesian optimization[J]. Southern power system technology, 2024, 18(9): 78-87, 105
[11] 朱会娟, 陈锦富, 李致远, 等. 基于多特征自适应融合的区块链异常交易检测方法[J]. 通信学报, 2021, 42(5): 41-50 ZHU Huijuan, CHEN Jinfu, LI Zhiyuan, et al. Block-chain abnormal transaction detection method based on adaptive multi-feature fusion[J]. Journal on communications, 2021, 42(5): 41-50
[12] CAI Jiahong, LIANG Wei, LI Xiong, et al. GTxChain: a secure IoT smart blockchain architecture based on graph neural network[J]. IEEE Internet of Things journal, 2023, 10(24): 21502-21514
[13] POURSAFAEI F, HAMAD G B, ZILIC Z. Detecting malicious ethereum entities via application of machine learning classification[C]//2020 2nd Conference on Blockchain Research & Applications for Innovative Networks and Services. Paris: IEEE, 2020: 120-127.
[14] NERURKAR P. Illegal activity detection on Bitcoin transaction using deep learning[J]. Soft computing, 2023, 27(9): 5503-5520
[15] CHEN Weili, GUO Xiongfeng, CHEN Zhiguang, et al. Phishing scam detection on ethereum: towards financial security for blockchain ecosystem[C]//Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. Yokohama: IJCAI, 2020: 4506-4512.
[16] JOURDAN M, BLANDIN S, WYNTER L, et al. Characterizing entities in the Bitcoin blockchain[EB/OL]. (2018-10-29)[2025-10-08]. https://arxiv.org/abs/1810.11956.
[17] RONG Yu, HUANG Wenbing, XU Tingyang, et al. DropEdge: towards deep graph convolutional networks on node classification[C]//International Conference on Learning Representations. New Orleans: OpenReview. net, 2019: 1-18.
[18] TIAN Yijun, PEI Shichao, ZHANG Xiangliang, et al. Knowledge distillation on graphs: a survey[J]. ACM computing surveys, 2025, 57(8): 1-16
[19] YANG Yiding, QIU Jiayan, SONG Mingli, et al. Distilling knowledge from graph convolutional networks[EB/OL]. (2020-03-23)[2025-10-08]. https://arxiv.org/abs/2003.10477.
[20] ZHOU Sheng, WANG Yucheng, CHEN Defang, et al. Distilling holistic knowledge with graph neural networks[EB/OL]. (2021-08-12)[2025-10-08]. https://arxiv.org/abs/2108.05507.
[21] ZHANG Liying, SUN Haihang. ESA-GCN: an enhanced graph-based node classification method for class imbalance using ENN-SMOTE sampling and an attention mechanism[J]. Applied sciences, 2024, 14(1): 111
[22] XU Keyulu, HU Weihua, LESKOVEC J, et al. How powerful are graph neural networks?[EB/OL]. (2018-10-01)[2025-10-08]. https://arxiv.org/abs/1810.00826.
[23] FIX E, HODGES J L. Discriminatory analysis. nonparametric discrimination: consistency properties[J]. Revue internationale de statistique, 1989, 57(3): 238
[24] DUDA R O, HART P E, STORK D G. Pattern Classification[M]. 2nd ed. New York: Wiley, 2001.
[25] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536
[26] COX D R. The regression analysis of binary sequences[J]. Journal of the royal statistical society series B (methodological), 1958, 20(2): 215-242
[27] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780
[28] CORTES C, VAPNIK V. Support-vector networks[J]. Machine learning, 1995, 20(3): 273-297
[29] 林伟. 基于多特征融合的区块链异常交易检测[J]. 信息网络安全, 2022, 22(10): 24-30 LIN Wei. Detection of abnormal transactions in blockchain based on multi feature fusion[J]. Netinfo security, 2022, 22(10): 24-30
[30] 谭朋柳, 周叶. 基于GAT与SVM的区块链异常交易检测[J]. 计算机应用研究, 2024, 41(1): 21-25,31 TAN Pengliu, ZHOU Ye. Blockchain anomaly transaction detection based on GAT and SVM[J]. Application research of computers, 2024, 41(1): 21-25,31
Similar References:

Memo

-

Last Update: 2026-09-05

Copyright © CAAI Transactions on Intelligent Systems