区块链技术广泛应用于数字资产和电子交易等行业。针对数字资产中的数据隐私性和数据资产交易的资金安全性难以保证的问题，本文提出基于零知识证明的区块链数字资产隐私访问策略和模块化决策森林的区块链交易欺诈检测模型。在数据层解决了用户的隐私信息被第三方泄漏风险和权限控制传递不明确的问题；在应用层面解决数字资产容易遭受不法节点的欺诈，导致财产损失的问题。本文主要研究内容如下：

第一，本文提出一种基于零知识证明的区块链数字资产隐私访问策略。此策略利用零知识证明思想对原始数据确权、存证与隐私保护，增强数据的可信度，保证数字资产的可信性和可用性。该访问策略包括用户注册、数据上传和验证、数据处理和访问控制三个阶段。用户注册阶段，以数字签名来明确所属关系，以避免将个人信息与账户相关联，从而降低关联泄露风险。在数据上传和验证阶段，采用 BGN(Boneh-Goh-Nissim, BGN)算法对原始数据进行加密，并用零知识证明验证数字资产的所有者。在访问控制阶段，为解决数据细粒度共享问题，提出一种基于 Shamir 的零知识密钥分配方案，并提高信息分割部分的安全性和个人隐私信息管理的效率。并从一致性分析、隐私性分析证明了所提系统的安全性。最终实验分析该系统的各个参数对运行时间的影响。

第二，针对区块链数字资产交易欺诈检测的有效性与精确性不足的问题，本文提出模块化决策森林的区块链交易欺诈检测模型。模块化决策森林是基于峰值密度快速模糊聚类算法将数据分解为多组小数据，每组数据都将由一个决策树学习。其次，模型根据隶属度确定模糊边界，模糊边界样本被添加到一组决策树学习。对于分类难度较大的样本采用多次划分，由父决策树与多个子决策树共同学习。最后，分别采用数字图像数据集 Optdigits、虚拟货币交易数据集 Elliptic 和 Ethereum，验证模块化决策森林模型的性能，并与图神经网络、逻辑回归等模型相对比。实验结果表明，模块化决策森林模型在精确率、召回率、F1-score 均有大幅提升，增幅范围分别是 1.2~7%、3.6~26.2%和 2.6~17.5%。

The blockchain technology has been widely applied in industries such as digital assets and electronic transactions. To address the issues of data privacy and fund security in digital asset transactions, this paper proposes a blockchain transaction fraud detection model based on zero-knowledge proof for privacy access to blockchain digital assets and a modular decision forest. The user's privacy risk of being leaked by third parties and the issue of unclear permission control in data transmission are addressed at the data level. Secondly, the problem of digital assets being susceptible to fraudulent nodes leading to property loss is resolved. The main research contents of this paper are as follows:

Firstly, a privacy access strategy for blockchain digital assets based on zero-knowledge proof is proposed. On one hand, by using the idea of zero-knowledge proof for the rightful claim, certification, storage, and privacy protection of original data, the credibility of data is enhanced, and the availability, credibility, and invisibility of digital assets are ensured. This access strategy includes three stages: user registration, data uploading and validation, and data processing and access control. In the user registration stage, digital signatures are used to confirm the relationship and avoid associating personal information with the account to reduce the risk of associated disclosure. In the data uploading and validation stage, the BGN algorithm is used to encrypt the original data, and zero-knowledge proof is used to verify the owner of the digital asset. In the access control stage, a zero-knowledge key distribution scheme based on Shamir is proposed to solve the problem of fine-grained data sharing, and the security of the information partition and the efficiency of personal privacy information management are improved. The security of the proposed system is demonstrated through consistency analysis and privacy analysis. Finally, the experimental analysis investigates the impact of various parameters of the system on the operating time.

Secondly, to address the issue of low effectiveness and accuracy of blockchain digitalasset transaction fraud detection, this dissertation proposes a modular decision forest-based blockchain transaction fraud detection model. The modular decision forest is based on peak density fast fuzzy clustering to decompose data into multiple small groups of data, each of which is learned by a decision tree. Then, the model determines the fuzzy boundary according to the membership degree, and the fuzzy boundary samples are learned by an additional decision tree. For samples with difficulty in classification, a multiple division strategy is adopted, in which the parent decision tree and multiple child decision trees learn together.

Finally, the performance of the modular decision forest model is verified using digital image datasets such as Optdigits, virtual currency transaction datasets such as Elliptic, and Ethereum, and is compared with other models such as graph neural networks, logistic regression, and random forests. Experimental results show that the modular decision forest model significantly improves precision, recall, and F1-score, with improvements ranging from 1.2% to 7%, 3.6% to 26.2%, and 2.6% to 17.5%, respectively

[1] 中共中央办公厅 国务院办公厅印发，关于推进实施国家文化数字化战略的意见 [J]. 国家图书馆学刊, 2022, 31(04): 49.

[2] 伍湘陵, 王思怡. 论数字资产保护的重要性 [J]. 中国科技产业, 2021, (09): 60–61.

[3] Wilson K B, Karg A, Ghaderi H. Prospecting non-fungible tokens in the digital economy:Stakeholders and ecosystem, risk and opportunity [J]. Business Horizons, 2022, 65(5):657–670.

[4] Hasan M, Starly B. Decentralized cloud manufacturing-as-a-service (CMaaS) platform architecture with configurable digital assets [J]. Journal of manufacturing systems, 2020, 56: 157–174.

[5] Mukhopadhyay U, Skjellum A, Hambolu O, et al. A brief survey of cryptocurrency systems[C]//2016 14th annual conference on privacy, security and trust (PST). IEEE, 2016: 745–752.

[6] Khan S N, Loukil F, Ghedira-Guegan C, et al. Blockchain smart contracts: Applications, challenges, and future trends [J]. Peer-to-peer Networking and Applications, 2021, 14: 2901–2925.

[7] Bandara E, Shetty S, Mukkamala R, et al. Casper: a blockchain-based system for efficient and secure customer credential verification [J]. Journal of Banking and Financial Technology, 2022, 6(1): 43–62.

[8] Li T, Wang H, He D, et al. Blockchain-based privacy-preserving and rewarding private data sharing for IoT [J]. IEEE Internet of Things Journal, 2022, 9(16): 15138–151549.

[9] Han X, Yuan Y, Wang F Y. A blockchain-based framework for central bank digital currency[C]//2019 IEEE International conference on service operations and logistics, and informatics (SOLI). IEEE, 2019: 263–268.

[10] 倪炀. 数字资产的产权保护对高质量发展的影响 [D]. 中南财经政法大学, 2021.

[11] Han B, Wang H, Qiao D, Xu J, Yan T. Application of Zero-Watermarking Scheme Based on Swin Transformer for Securing the Metaverse Healthcare Data. IEEE Journal of Biomedical and Health Informatics [J/OL] 2023, 10.1109/JBHI.2023.3 257340.

[12] West S M. Data capitalism: Redefining the logics of surveillance and privacy [J]. Business & society, 2019, 58(1): 20–41.

[13] Guo L, Xie H, Li Y. Data encryption based blockchain and privacy preserving mechanisms towards big data [J]. Journal of Visual Communication and Image Representation, 2020, 70: 1–11.

[14] Song R, Song Y, Liu Z, et al. GaiaWorld: a novel blockchain system based on competitive PoS consensus mechanism [J]. CMC-COMPUTERS MATERIALS & CONTINUA, 2019, 60(3): 973–987.

[15] Al Omar A, Rahman M S, Basu A, et al. Medibchain: A blockchain based privacy preserving platform for healthcare data[C]//Security, Privacy, and Anonymity in Computation, Communication, and Storage: SpaCCS 2017 International Workshops, Guangzhou, China, December 12-15, 2017, Proceedings 10. Springer International Publishing, 2017: 534–543.

[16] Ouaddah A, Abou Elkalam A, Ait Ouahman A. FairAccess: a new Blockchain‐based access control framework for the Internet of Things [J]. Security and communication networks, 2016, 9(18): 5943–5964.

[17] 董贵山,陈宇翔,范佳,郝尧,李枫.区块链应用中的隐私保护策略研究 [J]. 计算机科学, 2019, 46(05): 29–35.

[18] Ma Z, Jiang M, Gao H, et al. Blockchain for digital rights management [J]. Future Generation Computer Systems, 2018, 8(9): 746–764.

[19] Zhao C, Liu M, Yang Y, et al. Toward a blockchain based image network copyright transaction protection approach[C]//Security with Intelligent Computing and Big-data Services: Proceedings of the Second International Conference on Security with Intelligent Computing and Big Data Services (SICBS-2018) 2. Springer International Publishing, 2020: 17–28.

[20] Wu Y, Lu Z, Yu F, et al. Rapid consortium blockchain for digital right management[C]//Genetic and Evolutionary Computing: Proceedings of the Thirteenth International Conference on Genetic and Evolutionary Computing, November 1–3, 2019, Qingdao, China 13. Springer Singapore, 2020: 447–454.

[21] Guo J, Li C, Zhang G, et al. Blockchain-enabled digital rights management for multimedia resources of online education [J]. Multimedia Tools and Applications, 2020, 79: 9735–9755.

[22] Ober M, Katzenbeisser S, Hamacher K. Structure and anonymity of the bitcoin transaction graph [J]. Future internet, 2013, 5(2): 237–250.

[23] Reid F, Harrigan M. An analysis of anonymity in the bitcoin system [M]. Springer New York, 2013: 197–223.

[24] Koshy P, Koshy D, McDaniel P. An analysis of anonymity in bitcoin using p2p network traffic[C]//Financial Cryptography and Data Security: 18th International Conference, FC 2014, Christ Church, Barbados, March 3-7, 2014, Revised Selected Papers 18. Springer Berlin Heidelberg, 2014: 469–485.

[25] Li D, Liu W, Deng L, et al. Design of multimedia blockchain privacy protection system based on distributed trusted communication [J]. Transactions on Emerging Telecommunications Technologies, 2021, 32(2): 1–14.

[26] Song M, Sang Y, Zeng Y, et al. Blockchain-Based Secure Outsourcing of Fully Homomorphic Encryption Using Hidden Ideal Lattice[C]//Parallel and Distributed Computing, Applications and Technologies: 21st International Conference, PDCAT 2020, Shenzhen, China, December 28-30, 2020, Proceedings 21. Springer International Publishing, 2021: 154–165.

[27] Miyachi K, Mackey T K. hOCBS: A privacy-preserving blockchain framework for healthcare data leveraging an on-chain and off-chain system design [J]. Information processing & management, 2021, 58(3): 1–34.

[28] 周桐. 基于区块链技术的可信数据通证化方法的研究与应用 [D]. 中国科学技术大学, 2019.

[29] Chod J, Trichakis N, Tsoukalas G, et al. On the financing benefits of supply chain transparency and blockchain adoption [J]. Management science, 2020, 66(10): 4378–4396.

[30] Dunphy P, Petitcolas F A. A first look at identity management schemes on the blockchain [J]. IEEE security & privacy, 2018, 16(4): 20–29.

[31] PARK S, IM S, SEOL Y, et al. Nodes in the bitcoin network: Comparative measurement study and survey [J]. IEEE Access, 2019, 7: 57009–57022.

[32] Rahouti M, Xiong K, Ghani N. Bitcoin concepts, threats, and machine-learning security solutions [J]. Ieee Access, 2018, 6: 67189–67205.

[33] Gervais A, Karame G O, Capkun V, et al. Is bitcoin a decentralized currency? [J]. IEEE security & privacy, 2014, 12(3): 54–60.

[34] Soni A, Maheshwari S. A survey of attacks on the bitcoin system[C]//2018 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS). IEEE, 2018: 1–5.

[35] Rouhollahi Z. Towards Artificial Intelligence Enabled Financial Crime Detection [J/OL]2021,10.48550/arXiv.2105.10866.

[36] Chandradeva L S, Amarasinghe T M, De Silva M, et al. Monetary transaction fraud detection system based on machine learning strategies[C]//Fourth International Congress on Information and Communication Technology: ICICT 2019, London, Volume 1. Springer Singapore, 2020: 385–396.

[37] 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.

[38] Weber M, Domeniconi G, Chen J, et al. Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics [J/OL] 2019, 10.48550/arXiv.1908.02591.

[39] Kurshan E, Shen H, Yu H. Financial crime & fraud detection using graph computing: Application considerations & outlook[C]//2020 Second International Conference on Transdisciplinary AI (TransAI). IEEE, 2020: 125–130.

[40] Liao Q, Gu Y, Liao J, et al. Abnormal transaction detection of Bitcoin network based on feature fusion[C]//2020 IEEE 9th joint international information technology and artificial intelligence conference (ITAIC). IEEE, 2020, 9: 542–549.

[41] Li L, Chang X, Liu J, et al. Bit2cv: A novel bitcoin anti-fraud deposit scheme for connected vehicles [J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(7): 4181–4193.

[42] 高见, 孙懿, 王润正, 袁得嵛. 基于机器学习的浏览器挖矿检测模型研究 [J]. 计算机工程与应用, 2021, 57(22): 125–130.

[43] 黄彦春. 基于神经网络的快速模型预测控制算法研究 [D]. 浙江大学,2018.

[44] Kwon J. Tendermint: Consensus without mining [J]. Draft v. 0.6, fall, 2014, 1(11): 1–11.

[45] Elrom E. Neo blockchain and smart contracts [J]. The Blockchain Developer: A Practical Guide for Designing, Implementing, Publishing, Testing, and Securing Distributed Blockchain-based Projects, 2019, 257–598.

[46] Dai P, Mahi N, Earls J, et al. Smart-contract value-transfer protocols on a distributed mobile application platform [J]. Computer Science, 2017, 10, 1–27.

[47] Boneh D, Goh E J, Nissim K. Evaluating 2-DNF Formulas on Ciphertexts[C]//TCC. 2005, 3378: 325–341.

[48] Johnson D, Menezes A, Vanstone S. The elliptic curve digital signature algorithm (ECDSA) [J]. International journal of information security, 2001, 1: 36–63.

[49] Bacho R, Loss J. On the adaptive security of the threshold bls signature scheme[C]//Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. 2022: 193–207.

[50] Boneh D, Lynn B, Shacham H. Short signatures from the Weil pairing[C]//Advances in Cryptology — ASIACRYPT 2001: 7th International Conference on the Theory and Application of Cryptology and Information Security Gold Coast, Australia, December 9 –13, 2001 Proceedings 7. Springer Berlin Heidelberg, 2001: 514–532.

[51] Hopwood D, Bowe S, Hornby T, et al. Zcash protocol specification, [J/OL] 2020. https://github.com/zcash/zips/blob/master/protocol/protocol. pdf.

[52] Mayer H. Zk-SNARK explained: Basic Principles [J/OL] 2016. https://blog.coinfabrik. com/wp-content/uploads/2017/03/zkSNARK-explained_basic_principles. pdf.

[53] 贺东博. 基于同态加密和零知识证明的区块链隐私保护研究 [D] .华中科技大学, 2019.

[54] Gaba G S, Hedabou M, Kumar P, et al. Zero knowledge proofs based authenticated key agreement protocol for sustainable healthcare [J]. Sustainable Cities and Society, 2022, 80: 1–12 .

[55] Gabay D, Akkaya K, Cebe M. Privacy-preserving authentication scheme for connected electric vehicles using blockchain and zero knowledge proofs [J]. IEEE Transactions on Vehicular Technology, 2020, 69(6): 5760–5772.

[56] Feng T, Yang P, Liu C, et al. Blockchain data privacy protection and sharing scheme based on zero-knowledge proof [J]. Wireless Communications and Mobile Computing, 2022, 2022: 1–11.

[57] Dolev D, Yao A. On the security of public key protocols [J]. IEEE Transactions on information theory, 1983, 29(2): 198–208.

[58] Armando A, Basin D, Boichut Y, et al. The AVISPA tool for the automated validation of internet security protocols and applications[C]//Computer Aided Verification: 17th International Conference, CAV 2005, Edinburgh, Scotland, UK, July 6-10, 2005. Proceedings 17. Springer Berlin Heidelberg, 2005: 281–285.

[59] Panescu A T, Manta V. Smart contracts for research data rights management over the ethereum blockchain network [J]. Science & Technology Libraries, 2018, 37(3): 235–245.

[60] Nizamuddin N, Hasan H, Salah K, et al. Blockchain-based framework for protecting author royalty of digital assets [J]. Arabian Journal for Science and Engineering, 2019, 44: 3849–3866.

[61] Hasan H R, Salah K. Proof of delivery of digital assets using blockchain and smart contracts [J]. IEEE Access, 2018, 6: 65439–65448.

[62] Naz M, Al-zahrani F A, Khalid R, et al. A secure data sharing platform using blockchain and interplanetary file system [J]. Sustainability, 2019, 11(24): 1–24.

[63] Kripa M, Nidhin Mahesh A, Ramaguru R, et al. Blockchain framework for social media DRM based on secret sharing[C]//Information and Communication Technology for Intelligent Systems: Proceedings of ICTIS 2020, Volume 1. Springer Singapore, 2021: 451–458.

[64] 李莉,周斯琴,刘芹,何德彪.基于区块链的数字版权交易系统 [J]. 网络与信息安全学报, 2018, 4(07): 22–29.

[65] 袁勇, 王飞跃. 区块链技术发展现状与展望 [J]. 自动化学报, 2016, 42(04): 481-494.

[66] 田国华, 胡云瀚, 陈晓峰. 区块链系统攻击与防御技术研究进展 [J]. 软件学报, 2021, 32(05): 1495–1525.

[67] 李素,宋宝燕,李冬,王俊陆.面向金融活动的复合区块链关联事件溯源方法 [J]. 计算机科学, 2022, 49(03): 346–353.

[68] 檀超,张静宣,王铁鑫,岳涛.复杂软件系统的不确定性 [J].软件学报, 2021, 32(07):1926–1956.

[69] 喻文强,张艳梅,李梓宇,牛娃.以太坊庞氏骗局的类型分析与识别方法 [J]. 重庆大学学报, 2020, 43(11): 111–120.

[70] 林伟宁,陈明志,詹云清,刘川葆.一种基于PCA和随机森林分类的入侵检测算法研究[J]. 信息网络安全, 2017, (11): 50–54.

[71] 张昊,张小雨,张振友,李伟.基于深度学习的入侵检测模型综述 [J]. 计算机工程与应用, 2022, 58(6): 17–28.

[72] 张昭昭, 乔俊飞, 余文. 多层自适应模块化神经网络结构设计 [J]. 计算机学报, 2017, 40(12): 2827–2838.

[73] Johnson D, Sinanovic S. Symmetrizing the kullback-leibler distance [J]. IEEE Transactions on Information Theory, 2001, 1–11.

[74] Rodriguez A, Laio A. Clustering by fast search and find of density peaks [J]. science, 2014, 344(6191): 1492–1496.

[75] Cong Y, Yuan J, Liu J. Abnormal event detection in crowded scenes using sparse representation [J]. Pattern Recognition, 2013, 46(7): 1851–1864.

[76] Blake C. UCI repository of machine learning databases [DB/OL]. http://www. ics. uci. edu/~ mlearn/MLRepository. html, 1998.

[77] Vassallo D, Vella V, Ellul J. Application of gradient boosting algorithms for anti-money laundering in cryptocurrencies [J]. SN Computer Science, 2021, 2: 1–15.