透過您的圖書館登入
IP:18.117.82.179
  • 學位論文

使用軟體定義網路中MapReduce虛擬管理保護MapReduce網路隱私

Privacy Preserving for MapReduce Netwok using SDN with MapReduce Virtual Management

指導教授 : 鄭伯炤
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


MapReduce是近期快速興起的一門技術,用於分散式環境的大量資料平行運算。自從MapReduce服務提供給公司或大眾使用,提供資料隱私保護成為必要的條件。雖然在MapReduce網路中已經有很多改善資料隱私的方法,但是在MapReduce網路中,中間人攻擊(MITM)仍然很難防範,因此本研究想降低中間人攻擊對MapReduce網路所造成的隱私問題。 本論文改善了軟體定義網絡(SDN)架構用以保護MapReduce系統中資料傳輸的隱私,增加了MapReduce虛擬管理(MVM)至SDN架構中,MVM是一個虛擬化的應用程式,可以藉由分散和恢復資料的方式保護資料在傳輸時的隱私。MVM解決了安全和隱私上的問題。虛擬化可以使的系統更靈活、簡易和自動化。 我們說明了一般MapReduce隱私上的問題,並設計虛擬化的應用程式MVM解決問題,使得MapReduce網路可以有更好的資料隱私保護。

並列摘要


MapReduce, as the heart of Hadoop, become a new programming paradigm which has a good scalability to process big data in a distributed environment. However, data privacy poses a new challenge in cloud computing environment. Although many approaches have been proposed to improve the privacy of data in MapReduce network, Man-in-the-middle attack still remains unanswered. We propose a novel approach, called MapReduce virtual management (MVM), which uses Software Defined Networking (SDN) structure to enhance the data privacy protection. MVM is a virtualized SDN application which has benefits of simplicity, agility, and automation across the system. Experiment results show that MVM is able to route data properly with a low eavesdropping probability under different network topologies.

參考文獻


[1]Jeffrey Dean, Sanjay Ghemawat:MapReduce: simplified data processing on large clusters. Commun. ACM 51(1): 107-113 (2008)
[3]Bruno Astuto A. Nunes, Marc Mendonca, Xuan Nam Nguyen, Katia Obraczka, Thierry Turletti:A Survey of Software-Defined Networking: Past, Present, and Future of Programmable Networks. IEEE Communications Surveys and Tutorials 16(3): 1617-1634 (2014)
[5]S. Gueron:Intel Advanced Encryption Standard (AES) New Instructions Set. Intel Corporation, 2010
[6]J. Daemen, V. Rijmen:The Design of Rijndael: AES—The Advanced Encryption Standard, 2002
[7]He Li, Hai Jin:SDPMN: Privacy Preserving MapReduce Network Using SDN. International Conference on Cloud Computing and Big Data (CCBD) 2014:109 - 115

延伸閱讀