MVCG-SPS: A Multi-View Contrastive Graph Neural Network for Smart Ponzi Scheme Detection
Source abstract
Abstract
Detecting fraudulent activities such as Ponzi schemes within smart contract transactions is a critical challenge in decentralized finance. Existing methods often fail to capture the heterogeneous, multi-faceted nature of blockchain data, and many graph-based models overlook the contextual patterns that are vital for effective anomaly detection. In this paper, we propose MVCG-SPS, a Multi-View Contrastive Graph Neural Network designed to address these limitations. Our approach incorporates three key innovations: (1) Meta-Path-Based View Construction, which constructs multiple views of the data using meta-paths to capture different semantic relationships; (2) Reinforcement-Learning-Driven Multi-View Aggregation, which adaptively combines features from multiple views by optimizing aggregation weights through reinforcement learning; and (3) Multi-Scale Contrastive Learning, which aligns embeddings both within and across views to enhance representation robustness and improve anomaly detection performance. By leveraging a multi-view strategy, MVCG-SPS effectively integrates diverse perspectives to detect complex fraudulent behaviors in blockchain ecosystems. Extensive experiments on real-world Ethereum datasets demonstrated that MVCG-SPS consistently outperformed state-of-the-art baselines across multiple metrics, including F1 Score, AUPRC, and Rec@K. Our work provides a new direction for multi-view graph-based anomaly detection and offers valuable insights for improving security in decentralized financial systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Network Security and Intrusion Detection · Spam and Phishing Detection · Advanced Malware Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Beihang University, Beijing 100191, China
Tiande Company, Beijing 102400, China
References (42)
Show source-provided references
1. Anomaly detection in blockchain networks: A comprehensive survey10.1109/COMST.2022.3205643 ↗
2. Chen, W., Zheng, Z., Cui, J., Ngai, E., Zheng, P., and Zhou, Y. (2018, January 23–27). Detecting ponzi schemes on ethereum: Towards healthier blockchain technology. Proceedings of the 2018 World Wide Web Conference, Lyon, France.10.1145/3178876.3186046 ↗
3. A comprehensive survey on network anomaly detection10.1007/s11235-018-0475-8 ↗
4. Induction of decision trees10.1007/BF00116251 ↗
5. Anomaly detection: A survey10.1145/1541880.1541882 ↗
6. Callegari, C., Coluccia, A., D’Alconzo, A., and Giordano, S. (2013). A Methodological Overview on Anomaly Detection. Data Traffic Monitoring and Analysis, Springer.10.1007/978-3-642-36784-7_7 ↗
7. Deep learning10.1038/nature14539 ↗
8. Khan, S., and Yairi, T. (2021). A Review of Machine Learning and Deep Learning Techniques for Anomaly Detection. Appl. Sci., 11.
9. A comprehensive survey of anomaly detection techniques for high dimensional big data
10. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
11. Graph attention networks
12. Zhang, Z., Zhang, J., Xie, R., Dai, H., Yuan, B., Wang, W., and Philip, S.Y. (2021, January 14–18). FRAUDRE: Fraud Detection in Ethereum via Learning Representations of Transaction Subgraphs. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtually.
13. Liu, Y., Zheng, V.W., Zhao, Z., and Li, K.C.C. (2020, January 25–30). HeteroEmbed: Heterogeneous Information Network Embedding for Fraud Detection. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtually.
14. Graph Neural Networks for Multi-View Learning: A Taxonomic Review10.1007/s10462-024-10990-1 ↗
15. Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, F., and Bronstein, M. (2020). Temporal Graph Networks for Deep Learning on Dynamic Graphs. arXiv.
16. Yang, X., Li, X., Yang, J., Ming, Q., Wang, W., Tian, Q., and Yan, J. (2021). Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis. arXiv.
17. Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
18. Federici, M., Dutta, A., Forré, P., Kushman, N., and Akata, Z. (2020, January 30). Learning robust representations via multi-view information bottleneck. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia.
19. Graph contrastive learning with augmentations
20. Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., and Wang, L. (2021, January 19–23). Graph contrastive learning with adaptive augmentation. Proceedings of the Web Conference 2021, Ljubljana, Slovenia.10.1145/3442381.3449802 ↗
21. Liu, Y., Zheng, Y., Zhang, D., Lee, V.C., and Pan, S. (2023, January 8–10). Beyond smoothing: Unsupervised graph representation learning with edge heterophily discriminating. Proceedings of the AAAI conference on artificial intelligence, Montréal, QC, Canada.10.1609/aaai.v37i4.25573 ↗
22. Golan, I., and El-Yaniv, R. (2018, January 3–8). Deep anomaly detection using geometric transformations. Proceedings of the Advances in Neural Information Processing Systems, Montréal, QC, Canada.
23. Graph neural network for fraud detection via spatial-temporal attention10.1109/TKDE.2020.3025588 ↗
24. Graph based anomaly detection and description: A survey10.1007/s10618-014-0365-y ↗
25. A deep multi-view framework for anomaly detection on attributed networks
26. Adaloglou, N., Vretos, N., and Daras, P. (2020, January 23–28). Multi-view adaptive graph convolutions for graph classification. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XXVI 16.10.1007/978-3-030-58574-7_24 ↗
27. Tan, M.J., Zheng, Y., Li, Y.F., Gong, C., Zhou, C., and Pan, S. (2021, January 23–29). Multi-scale contrastive siamese networks for self-supervised graph representation learning. Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI). IJCAI, Virtually.
28. Ma, J., Chang, B., Zhang, X., and Mei, Q. (2020). Copulagnn: Towards integrating representational and correlational roles of graphs in graph neural networks. arXiv.
29. Schlichtkrull, M., Kipf, T.N., Bloem, P., Van Den Berg, R., Titov, I., and Welling, M. (2018, January 3–7). Modeling relational data with graph convolutional networks. Proceedings of the The semantic web: 15th international conference, ESWC 2018, Heraklion, Crete, Greece. proceedings 15.10.1007/978-3-319-93417-4_38 ↗
30. Vimal, S., Kayathwal, K., Wadhwa, H., and Dhama, G. (2021). Application of Deep Reinforcement Learning to Payment Fraud. arXiv.
31. Kim, H., Choi, J., and Whang, J.J. (2023). Dynamic Relation-Attentive Graph Neural Networks for Fraud Detection. arXiv.10.1109/ICDMW60847.2023.00143 ↗
32. SAMCL: Subgraph-Aligned Multiview Contrastive Learning for Graph Anomaly Detection10.1109/TNNLS.2023.3323274 ↗
33. Wu, T., Ren, J., Li, P., and Leskovec, J. (2020). Graph Information Bottleneck for Subgraph Recognition. arXiv.
34. Heterogeneous feature augmentation for ponzi detection in ethereum
35. Random forests10.1023/A:1010933404324 ↗
36. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
37. Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K. (2019, January 9–15). Simplifying graph convolutional networks. Proceedings of the International conference on machine learning. PMLR, Long Beach, CA, USA.
38. Xu, K., Hu, W., Leskovec, J., and Jegelka, S. (2019, January 6–9). How powerful are graph neural networks?. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA.
39. Hamilton, W.L., Ying, Z., and Leskovec, J. (2017, January 4–9). Inductive representation learning on large graphs. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
40. Busbridge, D., Sherburn, D., and Cavallo, P.L. (2019, January 8–14). Relational graph attention networks. Proceedings of the Graph Representation Learning Workshop, NeurIPS, Vancouver, BC, Canada.
41. Hu, Z., Dong, Y., Wang, K., and Sun, Y. (2020, January 6–10). Heterogeneous graph transformer. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtually.
42. Hassani, K., and Khasahmadi, A.H. (2020, January 13–18). Contrastive multi-view representation learning on graphs. Proceedings of the International Conference on Machine Learning. PMLR, Virtually.