跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 吳承翰
Cheng-Han Wu
論文名稱： 基於區塊鏈的聯邦學習決策樹建模平台設計:實現跨機構資料隱私保護之風險分析
Design of a Blockchain-Based Federated Learning Decision Tree Modeling Platform: Enabling Cross-Institutional Data Privacy with Risk Analysis
指導教授： 蔡孟峰
Meng-Feng Tsai
口試委員:
學位類別： 碩士
Master
系所名稱： 資訊電機學院 - 資訊工程學系
Department of Computer Science & Information Engineering
論文出版年： 2025
畢業學年度： 113
語文別： 中文
論文頁數： 43
中文關鍵詞： 區塊鏈 、智能合約 、連結攻擊 、決策樹
外文關鍵詞： blockchain, smart contract, link attack, decision tree
相關次數： 點閱：52  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 在跨機構資料整合的場景中，不同來源的資料往往存在高度潛在的關聯性，這雖帶來了整合分析的可能性，卻也衍生出隱私洩漏的風險，特別是當攻擊者掌握部分背景資訊時，便可能透過連結攻擊（link attack），推測或高度猜測出其他機構所管理的敏感資料內容，進而造成使用者資訊的間接暴露。這樣的風險使得資料無法安心流通與交換，即便已累積大量資料，也難以真正加以整合與轉化為具體價值，成為當前資料共享發展的一大瓶頸。
    本研究提出一個結合區塊鏈與聯邦學習建模的風險分析平台來實現跨機構建構決策樹的流程，區塊鏈和智能合約作為管理、協助和監督的角色，利用不可更改的特性，可以追溯平台上的所有動作，各機構可以在不直接共享原始資料的前提下，實現資料的整合與分析。同時，本研究對於決策樹建立過程中可能出現的隱私威脅提出分析並設計了保護機制，以保障機敏資料的隱私性與安全性。

    In the context of cross-institutional data integration, data from different sources often exhibit a high degree of potential correlation. While this offers possibilities for integrated analysis, it also gives rise to privacy leakage risks. Especially when an attacker possesses partial background information, they may launch link attacks to infer or closely approximate sensitive data managed by other parties, thereby potentially exposing user information indirectly. Such risks hinder the secure flow and exchange of data. Even with large volumes of collected data, effective integration and conversion into valuable insights remain challenging, constituting a major bottleneck in the advancement of data sharing today.
    This study proposes a risk analysis platform that combines blockchain and federated learning modeling to enable the construction of decision trees across institutions. Blockchain and smart contracts serve the roles of management, assistance, and supervision. By leveraging their immutable characteristics, all actions on the platform can be traced. Institutions can achieve data integration and analysis without directly sharing raw data. At the same time, this study analyzes potential privacy threats that may arise during the decision tree construction process and designs protection mechanisms to safeguard the privacy and security of sensitive data.

    摘要 i Abstract ii 誌謝 iii 目錄 iv 圖目錄 vi 表目錄 vii 一、緒論 1 1-1. 研究背景與動機 1 1-2. 研究目的 2 二、文獻探討 3 2-1. 區塊鏈 3 2-2. 以太坊 3 2-3. 智能合約 5 2-4. 星際檔案系統 5 2-5. 聯邦學習 6 2-6. 連結攻擊 8 三、系統架構與流程 10 3-1. 系統環境與平台架構 10 3-2. 系統開發流程 11 四、研究方法 13 4-1. 定義平台角色 13 4-1-1. 平台方 13 4-1-2. 組織方 13 4-2. 提案協作流程 13 4-2-1. 註冊申請及審核 14 4-2-2. 提案提交及分派 14 4-3. 聯邦學習建樹流程 15 4-4. 連結攻擊分析及建樹流程調整 16 4-4-1. 連結攻擊形式一 16 4-4-2. 連結攻擊形式二 17 4-4-3. 建樹方法調整 18 4-5. 資料儲存 20 4-6. 智能合約設計 21 4-6-1. Register Org 22 4-6-2. Create Task 22 4-6-3. Upload Result 22 4-6-4. Download Result 23 五、實驗 24 5-1. 實驗規格與環境 24 5-2. 實驗資料集 24 5-3. 決策樹比較 26 5-4. 特徵重要性與條件熵比較 27 5-5. 智能合約費用 28 六、結論 30 七、參考文獻 31

    [1] S. Nakamoto, "Bitcoin: A peer-to-peer electronic cash system," 2008.
    [2] C. Dwork and M. Naor, "Pricing via processing or combatting junk mail," in Advances in Cryptology—CRYPTO’92, Lecture Notes in Computer Science, vol. 740, Springer, 1993, pp. 139–147.Leslie Lamport, Robert Shostak, Marshall Pease . "The Byzantine Generals Problem." 1982.
    [3] L. Lamport, R. Shostak, and M. Pease, “The Byzantine Generals Problem,” ACM Trans. Program. Lang. Syst., vol. 4, no. 3, pp. 382–401, Jul. 1982.G. Wood, "Ethereum: A secure decentralised generalised transaction ledger,"Ethereum project yellow paper, vol. 151, no. 2014, pp. 1-32, 2014.
    [4] National Institute of Standards and Technology, “SHA‑3 Standard: Permutation‑Based Hash and Extendable‑Output Functions,” FIPS PUB 202, Aug. 2015.
    [5] G. Wood, "Ethereum: A secure decentralised generalised transaction ledger," Ethereum project yellow paper, vol. 151, no. 2014, pp. 1-32, 2014.
    [6] E. Hildenbrandt et al., “KEVM: A Complete Formal Semantics of the Ethereum Virtual Machine,” in Proc. CSF, 2018.
    [7] V. Buterin and V. Griffith, “Casper the Friendly Finality Gadget,” arXiv:1710.09437, Oct. 2017.
    [8] K. Christidis and M. Devetsikiotis, “Blockchains and Smart Contracts for the Internet of Things,” IEEE Access, vol. 4, pp. 2292–2303, 2016.
    [9] J. Benet, “IPFS – Content‑Addressed, Versioned, P2P File System,” arXiv:1407.3561, Jul. 2014.
    [10] B. McMahan, E. Moore, D. Ramage, S. Hampson and B. Aguera‑y‑Arcas, Communication‑Efficient Learning of Deep Networks from Decentralized Data,” in Proc. AISTATS, 2017.
    [11] J. Weber, M. Gurtner, A. Lobe, A. Trachte, and A. Kugi, “Combining Federated Learning and Control: A Survey,” arXiv:2407.11069, Jul. 2024.
    [12] McMahan, B., et al., “Link Inference Attacks in Vertical Federated Graph Learning,” 2024.
    [13] MetaMask, “A crypto wallet & gateway to blockchain apps,” ConsenSys, 2024. [Online]. Available: https://metamask.io/ [Accessed: Jun. 30, 2025].
    [14] Truffle Suite, “Ganache – Personal blockchain for Ethereum development,” 2024. [Online]. Available: https://trufflesuite.com/ganache/ [Accessed: Jun. 30, 2025].
    [15] Docker Inc., “Docker – Empowering app development for developers,” 2024. [Online]. Available: https://www.docker.com/ [Accessed: Jun. 30, 2025].
    [16] Ethereum Foundation, “Remix IDE – Ethereum IDE for smart contract development,” 2024. [Online]. Available: https://remix.ethereum.org/ [Accessed: Jun. 30, 2025].
    [17] Ethereum Foundation, “Web3.js – Ethereum JavaScript API,” 2024. [Online]. Available: https://web3js.readthedocs.io/ [Accessed: Jun. 30, 2025].
    [18] K. Cheng, T. Fan, Y. Jin, Y. Liu, T. Chen, D. Papadopoulos, and Q. Yang, “SecureBoost: A Lossless Federated Learning Framework,” arXiv:1901.08755, Jan. 2019.
    [19] J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” *Annals of Statistics*, vol. 29, no. 5, pp. 1189–1232, 2001.
    [20] C. E. Shannon, “A mathematical theory of communication,” *Bell System Technical Journal*, vol. 27, no. 3–4, pp. 379–423 & 623–656, 1948.

    QR CODE
    :::