基于深度学习的区块链数据分析

     随着区块链技术的持续发展和广泛应用，区块链系统中产生的大量交易数据给系统的维护和监管带来了巨大挑战。区块链数据分析作为一种对区块链数据进行探索分析的重要技术，能够及时发现和处理区块链中的异常交易行为和异常账户，从而确保系统的稳定运行和金融安全。然而，现有的基于机器学习和图神经网络等技术的区块链数据分析方法普遍存在标签依赖等局限性，影响了其应用范围。为了解决上述难点，本研究以区块链账户分类为核心研究问题，采用类别不平衡分类、图表示学习和强化学习相结合的方法，旨在解决区块链数据中的类别不平衡问题，促进区块链数据分析技术的发展和应用。

    针对区块链数据的类别不平衡问题，本研究提出了一种基于最近邻数据增强的区块链账户分类方法。该方法利用最近邻高斯混合技术合成少数类样本，并通过边生成器将合成样本连接到原始图中，然后使用增强数据训练分类模型，以提高其分类性能。由于前述过采样方法依赖启发式规则，存在对数据分布敏感和容易过拟合等问题，本研究进一步提出了一种基于强化学习的自适应过采样方法。该方法利用强化学习的思想，通过训练智能体来动态调整过采样策略，以合成更符合真实数据分布的样本。本研究基于真实交易数据构建了区块链交易网络，并对其进行了深入的实验分析。实验结果表明，本研究提出的两种方法都能有效提高过采样的效率，在区块链账户分类任务上的表现均优于其他基线方法。

   通过引入最近邻高斯混合和自适应过采样两种创新的数据增强策略，本研究分别设计了两种区块链账户分类方法，有效解决了类别不平衡问题，并扩展了现有区块链数据分析方法的设计思路。此外，本研究的思想和方法同样适用于图数据分析领域，能有效缓解图数据类别不平衡带来的影响，有较广泛的应用场景。

   With the continuous development and widespread application of blockchain technology, a vast volume of transaction data generated within the blockchain system brings great challenges to the maintenance and supervision of the system. Blockchain data analysis, a pivotal technique for exploring and analyzing blockchain data, plays a key role in the timely identification and remediation of anomalous transaction behaviors and accounts, thereby ensuring the system's stability and financial security. However, current methods of blockchain data analysis, predominantly based on machine learning and graph neural network, face significant constraints such as reliance on labeled data, which limits their applicability. To address these challenges, this study focuses on blockchain accounts classification, utilizing a combination of methods such as class imbalanced classification, graph representation learning, and reinforcement learning. The goal of this study is to address the issue of class imbalance in blockchain data and advance the development and application of blockchain data analytics technologies.

   To address the issue of class imbalance in blockchain data, this study introduces a blockchain account classification method based on nearest neighbor data augmentation. This method employs the nearest neighbor Gaussian Mixup technique to synthesize minority class samples and integrates these samples into the original graph through an edge generator. The augmented data is then used to train the classification model, significantly enhancing its efficacy.Given that the aforementioned oversampling method relies on heuristic rules, making it sensitive to data distribution and prone to overfitting, this research further introduces an adaptive over-sampling method based on reinforcement learning. Utilizing the principles of reinforcement learning, this method adaptively adjusts the over-sampling strategy via the training of an intelligent agent, to synthesize samples that more accurately mirror the real data distribution. In this research,  blockchain transaction networks were constructed using real transaction data, and a comprehensive experimental analysis was conducted. The results indicate that both methods proposed by this study significantly improve the efficiency of over-sampling and outperform other baseline methods in the task of blockchain account classification.  

   By introducing two innovative data augmentation strategies: nearest neighbor Gaussian Mixup and adaptive over-sampling, this research has developed unique blockchain account classification methods, effectively addressing the class imbalance problem and broadening the conceptual framework of existing blockchain data analysis methods. Moreover, the principles and techniques proposed in this study are equally applicable to the domain of graph data analysis. They can significantly mitigate the effects of class imbalance in graph data, thus presenting a wide range of potential applications.

[1] NAKAMOTO S. Bitcoin: A Peer-to-Peer Electronic Cash System[Z]. 2008.
[2] 澎湃新闻网. 国内首笔银行区块链业务上线：微众银行用区块链清算联合贷款[EB/OL].(2016-09-24)
[2022-10-10]. https://www.thepaper.cn/newsDetail_forward_1533899.
[3] 智能制造网. 基于区块链技术的零件溯源让汽配产品变得更加安全[EB/OL]. (2018-07-27)
[2022-10-10]. https://www.gkzhan.com/news/Detail/110492.html.
[4] SARANYA R, MURUGAN A. A systematic review of enabling blockchain in healthcare sys tem: Analysis, current status, challenges and future direction[J]. Materials Today: Proceedings,2023, 80: 3010-3015.
[5] HUO R, ZENG S, WANG Z, et al. A Comprehensive Survey on Blockchain in Industrial Internet of Things: Motivations, Research Progresses, and Future Challenges[J]. IEEE Communications Surveys & Tutorials, 2022, 24(1): 88-122.
[6] 新华网. 习近平在中央政治局第十八次集体学习时强调把区块链作为核心技术自主创新重要突破口加快推动区块链技术和产业创新发展[EB/OL]. (2019-10-25)
[2022-10-10].http://www.xinhuanet.com/politics/leaders/2019-10/25/c_1125153665.htm.
[7] 央视网. 国家发展改革委首次明确“新基建”范围[EB/OL]. (2020-04-21)
[2022-10-10].https://news.cctv.com/2020/04/21/ARTI6QObJe1pP8e87BYyQ5fp200421.shtml.
[8] 工业互联网产业联盟. 工业区块链应用白皮书[EB/OL]. (2019-02)
[2022-10-10]. http://www.aii-alliance.org/upload/202003/0302_110455_445.pdf.
[9] YAGA D, MELL P, ROBY N, et al. Blockchain Technology Overview[A]. 2019.
[10] BMWI B F W U E. Blockchain-Strategie der Bundesregierung[EB/OL]. (2019-09-18)
[2022-10-10]. https://www.bmwk.de/Redaktion/DE/Publikationen/Digitale-Welt/blockchain-strategie.html.
[11] DEPARTMENT OF INDUSTRY E, Science, (DISER) R. National blockchain roadmap: Pro gressing towards a blockchain-empowered future[M]. Australian Government Australia, 2020.
[12] CoinGecko. Global Cryptocurrency Market Cap charts[EB/OL]. 2022
[2022-10-10]. https://www.coingecko.com/en/global-charts.
[13] CHAINALYSIS. 2021-Crypto-Crime-Report[EB/OL].
[2022-10-10]. https://go.chainalysis.com/2021-Crypto-Crime-Report.html.
[14] SAAD M, THAI M T, MOHAISEN A. POSTER: Deterring DDoS Attacks on Blockchain based Cryptocurrencies through Mempool Optimization[C]//Proceedings of the 2018 on Asiaconference on computer and communications security. 2018: 809-811.
[15] VASEK M, MOORE T. There’s No Free Lunch, Even Using Bitcoin: Tracking the Popularityand Profits of Virtual Currency Scams[C]//Financial Cryptography and Data Security: 19th In ternational Conference, FC 2015, San Juan, Puerto Rico, January 26-30, 2015, Revised Selected Papers 19. Springer, 2015: 44-61.
[16] LI J, GU C, WEI F, et al. A Survey on Blockchain Anomaly Detection Using Data Mining Tech niques[C]//Blockchain and Trustworthy Systems: First International Conference, BlockSys2019, Guangzhou, China, December 7–8, 2019, Proceedings 1. Springer, 2020: 491-504.
[17] HUYNH T T, NGUYEN T D, TAN H. A Survey on Security and Privacy Issues of BlockchainTechnology[C]//2019 international conference on system science and engineering (ICSSE).IEEE, 2019: 362-367.
[18] ZAMBRE D, SHAH A. Analysis of Bitcoin Network Dataset for Fraud[J]. unpublished Report,2013, 27: 2013.
[19] PHAM T B, LEE S. Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods: abs/1611.03941[A/OL]. 2016. https://api.semanticscholar.org/CorpusID:16069399.
[20] MONAMO P, MARIVATE V, TWALA B. Unsupervised learning for robust Bitcoin fraud detection[C]//2016 Information Security for South Africa (ISSA). IEEE, 2016: 129-134.
[21] TOYODA K, OHTSUKI T, MATHIOPOULOS P T. Identification of High Yielding Invest ment Programs in Bitcoin via Transactions Pattern Analysis[C]//GLOBECOM 2017-2017 IEEEGlobal Communications Conference. IEEE, 2017: 1-6.
[22] BOGNER A. Seeing is understanding: anomaly detection in blockchains with visualized fea tures[C]//Proceedings of the 2017 ACM international joint conference on pervasive and ubiqui tous computing and proceedings of the 2017 ACM international symposium on wearable com puters. 2017: 5-8.
[23] BARTOLETTI M, PES B, SERUSI S. Data Mining for Detecting Bitcoin Ponzi Schemes[C]//2018 crypto valley conference on blockchain technology (CVCBT). IEEE, 2018: 75-84.
[24] CHEN W, ZHENG Z, NGAI E C H, et al. Exploiting Blockchain Data to Detect Smart Ponzi Schemes on Ethereum[J]. IEEE Access, 2019, 7: 37575-37586.
[25] SAYADI S, REJEB S B, CHOUKAIR Z. Anomaly Detection Model Over Blockchain Elec tronic Transactions[C]//2019 15th international wireless communications & mobile computing conference (IWCMC). IEEE, 2019: 895-900.
[26] ZOLA F, EGUIMENDIA M, BRUSE J L, et al. Cascading Machine Learning to Attack Bitcoin Anonymity[C]//2019 IEEE International Conference on Blockchain (Blockchain). IEEE, 2019: 10-17.
[27] CHEN W, GUO X, CHEN Z, et al. Phishing Scam Detection on Ethereum: Towards Financial Security for Blockchain Ecosystem[C]//IJCAI: Vol. 7. 2020: 4456-4462.
[28] WEBER M, DOMENICONI G, CHEN J, et al. Anti-Money Laundering in Bitcoin: Experi menting with Graph Convolutional Networks for Financial Forensics[C]//ACM SIGKDD In ternational Conference on Knowledge Discovery and Data Mining. 2019.
[29] WU J, YUAN Q, LIN D, et al. Who Are the Phishers? Phishing Scam Detection on Ethereum via Network Embedding[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 52(2): 1156-1166.
[30] GROVER A, LESKOVEC J. node2vec: Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 2016: 855-864.
[31] SCICCHITANO F, LIGUORI A, GUARASCIO M, et al. Deep Autoencoder Ensembles forAnomaly Detection on Blockchain[C]//Foundations of Intelligent Systems: 25th International Symposium, ISMIS 2020, Graz, Austria, September 23–25, 2020, Proceedings. Springer, 2020: 448-456.
[32] CHEN L, PENG J, LIU Y, et al. Phishing Scams Detection in Ethereum Transaction Network[J]. ACM Transactions on Internet Technology (TOIT), 2020, 21(1): 1-16.
[33] LIN D, WU J, YUAN Q, et al. Modeling and Understanding Ethereum Transaction Records via a Complex Network Approach[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2020, 67(11): 2737-2741.
[34] LI S, WANG R, WU H, et al. SIEGE: Self-Supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection[C]//Proceedings of the 31st ACM International Conference on Multimedia. 2023: 8881-8890.
[35] HU T, LIU X, CHEN T, et al. Transaction-based classification and detection approach for Ethereum smart contract[J]. Information Processing & Management, 2021, 58(2): 102462.
[36] HOCHREITER S, SCHMIDHUBER J. Long Short-Term Memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[37] POURSAFAEI F, RABBANY R, ZILIC Z. SigTran: Signature Vectors for Detecting Illicit Ac tivities in Blockchain Transaction Networks[C]//Pacific-Asia Conference on Knowledge Dis covery and Data Mining. Springer, 2021: 27-39.
[38] LIU J, ZHENG J, WU J, et al. FA-GNN: Filter and Augment Graph Neural Networks for Ac count Classification in Ethereum[J]. IEEE Transactions on Network Science and Engineering, 2022, 9(4): 2579-2588.
[39] LI S, GOU G, LIU C, et al. TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection[C]//Proceedings of the ACM Web Conference 2022. 2022:661-669.
[40] HUANG T, LIN D, WU J. Ethereum Account Classification Based on Graph Convolutional Network[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2022, 69(5): 2528-2532.
[41] YU T, CHEN X, XU Z, et al. MP-GCN: A Phishing Nodes Detection Approach via Graph Convolution Network for Ethereum[J]. Applied Sciences, 2022, 12(14): 7294.
[42] FU B, YU X, FENG T. CT-GCN: a phishing identification model for blockchain cryptocurrency transactions[J]. International Journal of Information Security, 2022, 21(6): 1223-1232.
[43] YU L, JING Q, LI R, et al. ParGCN: Abnormal Transaction Detection based on Graph Neural Networks[C]//2022 IEEE 22nd International Conference on Software Quality, Reliability and Security (QRS). IEEE, 2022: 797-808.
[44] HOU W, CUI B, LI R. Detecting Phishing Scams on Ethereum Using Graph Convolutional Networks with Conditional Random Field[C]//2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2022: 1495-1500.
[45] HU S, ZHANG Z, LUO B, et al. BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection[C]//Proceedings of the ACM Web Conference 2023. 2023: 2189-2197.
[46] WANG L, XU M, CHENG H. Phishing scams detection via temporal graph attention network in Ethereum[J]. Information Processing & Management, 2023, 60(4): 103412.
[47] BEHFAR S K, CROWCROFT J. Probabilistic Sampling-Enhanced Temporal-SpatialGCN: A Scalable Framework for Transaction Anomaly Detection in Ethereum Networks:abs/2310.00144[A/OL]. 2023. https://api.semanticscholar.org/CorpusID:263334355.
[48] HAN B, WEI Y, WANG Q, et al. MT2AD: multi-layer temporal transaction anomaly detection in ethereum networks with GNN[J/OL]. Complex & Intelligent Systems, 2023, 10: 613-626. https://api.semanticscholar.org/CorpusID:260390517.
[49] LIN Z, XIAO X, HU G, et al. Tracking phishing on Ethereum: Transaction network embedding approach for accounts representation learning[J]. Computers & Security, 2023, 135: 103479.
[50] ZHAO L, SEN GUPTA S, KHAN A, et al. Temporal Analysis of the Entire EthereumBlockchain Network[C]//Proceedings of the Web Conference 2021. 2021: 2258-2269.
[51] THARANI J S, CHARLES E Y A, HóU Z, et al. Graph Based Visualisation Techniques for Analysis of Blockchain Transactions[C/OL]//2021 IEEE 46th Conference on Local Computer Networks (LCN). 2021: 427-430. DOI: 10.1109/LCN52139.2021.9524878.
[52] STROGATZ S H. Exploring complex networks[J]. nature, 2001, 410(6825): 268-276.
[53] LEE S H, KIM P J, JEONG H. Statistical properties of sampled networks[J]. Physical review E, 2006, 73(1): 016102.
[54] NEWMAN M E. Assortative mixing in networks[J]. Physical review letters, 2002, 89(20):208701.
[55] KURANT M, MARKOPOULOU A, THIRAN P. Towards Unbiased BFS Sampling[J]. IEEE Journal on Selected Areas in Communications, 2011, 29(9): 1799-1809.
[56] LESKOVEC J, FALOUTSOS C. Sampling from Large Graphs[C]//Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining. 2006: 631-636.
[57] LI X, SUN L, LING M, et al. A survey of graph neural network based recommendation in social networks[J]. Neurocomputing, 2023: 126441.
[58] JIANG W, LUO J. Graph neural network for traffic forecasting: A survey[J]. Expert Systems with Applications, 2022, 207: 117921.
[59] RÉAU M, RENAUD N, XUE L C, et al. DeepRank-GNN: a graph neural network framework to learn patterns in protein–protein interfaces[J]. Bioinformatics, 2023, 39(1): btac759.
[60] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: Online Learning of Social Representations[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014: 701-710.
[61] KIPF T N, WELLING M. Semi-Supervised Classification with Graph Convolutional Networks[C]//International Conference on Learning Representations. 2016.
[62] CHIANG W L, LIU X, SI S, et al. Cluster-GCN: An Efficient Algorithm for Training Deep andLarge Graph Convolutional Networks[C]//Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019: 257-266.
[63] VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks:abs/1710.10903[A/OL]. 2017. https://api.semanticscholar.org/CorpusID:3292002.
[64] DWIVEDI V P, BRESSON X. A Generalization of Transformer Networks to Graphs[A]. 2020.
[65] HAMILTON W, YING Z, LESKOVEC J. Inductive Representation Learning on Large Graphs[J]. Advances in neural information processing systems, 2017, 30.
[66] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: Synthetic Minority Over-sampling Technique[J]. Journal of artificial intelligence research, 2002, 16: 321-357.
[67] HAN H, WANG W Y, MAO B H. Borderline-SMOTE: A New Over-Sampling Method in Im balanced Data Sets Learning[C]//International conference on intelligent computing. Springer,2005: 878-887.
[68] HE H, BAI Y, GARCIA E A, et al. ADASYN: Adaptive synthetic sampling approach for imbalanced learning[C]//2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence). Ieee, 2008: 1322-1328.
[69] PRADIPTA G A, WARDOYO R, MUSDHOLIFAH A, et al. SMOTE for Handling Imbal anced Data Problem : A Review[C]//2021 sixth international conference on informatics and computing (ICIC). IEEE, 2021: 1-8.
[70] TANG B, HE H. ENN: Extended Nearest Neighbor Method for Pattern Recognition [Research Frontier][J]. IEEE Computational intelligence magazine, 2015, 10(3): 52-60.
[71] ELHASSAN T, ALJURF M. Classification of Imbalance Data using Tomek Link(T-Link) Com bined with Random Under-sampling (RUS) as a Data Reduction Method[J]. Global J Technol Optim S, 2016, 1: 2016.
[72] BATISTA G E, PRATI R C, MONARD M C. A study of the behavior of several methods for balancing machine learning training data[J]. ACM SIGKDD explorations newsletter, 2004, 6(1): 20-29.
[73] ZHAO T, ZHANG X, WANG S. GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks[C]//Proceedings of the 14th ACM international conference on web search and data mining. 2021: 833-841.
[74] WU L, XIA J, GAO Z, et al. GraphMixup: Improving Class-Imbalanced Node Classification by Reinforcement Mixup and Self-supervised Context Prediction[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 2022: 519-535.
[75] PARK J, SONG J, YANG E. GraphENS: Neighbor-Aware Ego Network Synthesis for Class Imbalanced Node Classification[C]//International conference on learning representations. 2021.
[76] YUAN B, MA X. Sampling + reweighting: Boosting the performance of AdaBoost on imbal anced datasets[M]//The 2012 international joint conference on neural networks (IJCNN). IEEE,2012: 1-6.
[77] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2980-2988.
[78] CUI Y, JIA M, LIN T Y, et al. Class-Balanced Loss Based on Effective Number of Samples[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019:9268-9277.
[79] CHEN D, LIN Y, ZHAO G, et al. Topology-Imbalance Learning for Semi-Supervised Node Classification[J]. Advances in Neural Information Processing Systems, 2021, 34: 29885-29897.
[80] EL MRABET M A, EL MAKKAOUI K, FAIZE A. Supervised Machine Learning: A Survey[C]//2021 4th International Conference on Advanced Communication Technologies and Net working (CommNet). IEEE, 2021: 1-10.
[81] 陈海虹, 黄彪, 刘峰, 等. 机器学习原理及应用[M]. 成都: 电子科技大学出版社, 2017: 2-19.
[82] PUTERMAN M L. Markov Decision Processes[J]. Wiley Series in Probability and Statistics,1994.
[83] RUAN A, SHI A, QIN L, et al. A Reinforcement Learning-Based Markov-Decision Process (MDP) Implementation for SRAM FPGAs[J]. IEEE Transactions on Circuits and Systems II:Express Briefs, 2019, 67(10): 2124-2128.
[84] 刘全, 翟建伟, 章宗长, 等. 深度强化学习综述[J]. 计算机学报, 2018, 41(1): 1-27.
[85] WATKINS C J C H. Learning From Delayed Rewards[M]. King’s College, Cambridge United Kingdom, 1989.
[86] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Playing Atari with Deep Reinforcement Learning[A]. 2013.
[87] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforce ment learning[J]. nature, 2015, 518(7540): 529-533.
[88] LIN L J. Reinforcement learning for robots using neural networks[M]. Carnegie Mellon Uni versity, 1992.
[89] VAN HASSELT H, GUEZ A, SILVER D. Deep Reinforcement Learning with Double Q Learning[C]//Proceedings of the AAAI conference on artificial intelligence: Vol. 30. 2016.
[90] SUTTON R S, MCALLESTER D, SINGH S, et al. Policy Gradient Methods for Reinforcement Learning with Function Approximation[J]. Advances in neural information processing systems,1999, 12.
[91] WILLIAMS R J. Simple statistical gradient-following algorithms for connectionist reinforce ment learning[J]. Machine learning, 1992, 8: 229-256.
[92] SCHULMAN J, MORITZ P, LEVINE S, et al. High-Dimensional Continuous Control Using Generalized Advantage Estimation[J/OL]. CoRR, 2015, abs/1506.02438. https://api.semantic scholar.org/CorpusID:3075448.
[93] SCHULMAN J, LEVINE S, ABBEEL P, et al. Trust Region Policy Optimization[C]//International conference on machine learning. PMLR, 2015: 1889-1897.
[94] KONDA V, TSITSIKLIS J. Actor-Critic Algorithms[J]. Advances in neural information pro cessing systems, 1999, 12.
[95] LILLICRAP T P, HUNT J J, PRITZEL A, et al. Continuous control with deep reinforcement learning[J/OL]. CoRR, 2015, abs/1509.02971. https://api.semanticscholar.org/CorpusID:16326763.
[96] SCHULMAN J, WOLSKI F, DHARIWAL P, et al. Proximal Policy Optimization Algorithms:abs/1707.06347[A/OL]. 2017. https://api.semanticscholar.org/CorpusID:28695052.
[97] ZHENG P, ZHENG Z, WU J, et al. XBlock-ETH: Extracting and Exploring Blockchain Data From Ethereum[J]. IEEE Open Journal of the Computer Society, 2020, 1: 95-106.
[98] CHEN T, LI Z, ZHU Y, et al. Understanding Ethereum via Graph Analysis[J]. ACM Transac tions on Internet Technology (TOIT), 2020, 20(2): 1-32.
[99] LEE X T, KHAN A, SEN GUPTA S, et al. Measurements, Analyses, and Insights on the Entire Ethereum Blockchain Network[C]//Proceedings of The Web Conference 2020. 2020: 155-166.
[100] LI Y, ISLAMBEKOV U, AKCORA C, et al. Dissecting Ethereum Blockchain Analytics: What We Learn from Topology and Geometry of the Ethereum Graph?[C]//Proceedings of the 2020 SIAM international conference on data mining. SIAM, 2020: 523-531.
[101] LIN D, WU J, YUAN Q, et al. T-EDGE: Temporal WEighted MultiDiGraph Embedding for Ethereum Transaction Network Analysis[J/OL]. Frontiers in Physics, 2020, 8. https://www.frontiersin.org/articles/10.3389/fphy.2020.00204.
[102] OFORI-BOATENG D, DOMINGUEZ I S, AKCORA C, et al. Topological Anomaly Detection in Dynamic Multilayer Blockchain Networks[C]//Machine Learning and Knowledge Discov ery in Databases. Research Track: European Conference, ECML PKDD 2021, Bilbao, Spain, September 13–17, 2021, Proceedings, Part I 21. Springer, 2021: 788-804.
[103] CASALE-BRUNET S, RIBECA P, DOYLE P, et al. Networks of Ethereum Non-Fungible Tokens: A graph-based analysis of the ERC-721 ecosystem[C]//2021 IEEE International Con ference on Blockchain (Blockchain). IEEE, 2021: 188-195.
[104] WANG Q, ZHANG Z, LIU Z, et al. ETGraph: A Pioneering Dataset Bridging Ethereum and Twitter: abs/2310.01015[A/OL]. 2023. https://api.semanticscholar.org/CorpusID:263605800.
[105] BLOCKCHAIN.COM. Blockchain Explorer[EB/OL].
[2022-10-10]. https://www.blockchain.com/explorer.
[106] DONG H, FRUSQUE G, ZHAO Y, et al. NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation[A]. 2023.
[107] ANDO S, HUANG C Y. Deep Over-sampling Framework for Classifying Imbalanced Data[C]//Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2017, Skopje, Macedonia, September 18–22, 2017, Proceedings, Part I 10. Springer,2017: 770-785.