互聯(lián)網(wǎng)和物聯(lián)網(wǎng)的快速發(fā)展開(kāi)啟了信息時(shí)代的新紀(jì)元,數(shù)據(jù)呈現(xiàn)數(shù)量龐大、類型繁多、增速快、價(jià)值密度低和真實(shí)性等特性。機(jī)器學(xué)習(xí)作為實(shí)現(xiàn)人工智能的途徑,重點(diǎn)研究如何從海量數(shù)據(jù)中獲取隱藏的、有效的、可理解的知識(shí),建立數(shù)據(jù)驅(qū)動(dòng)型的推理與決策模型,實(shí)現(xiàn)“取之于數(shù)據(jù),用之于數(shù)據(jù)”的目標(biāo)。然而,傳統(tǒng)的機(jī)器學(xué)習(xí)算法通常包含計(jì)算密集型的學(xué)習(xí)過(guò)程,對(duì)于資源受限的終端用戶來(lái)說(shuō)存在應(yīng)用局限性。此外,訓(xùn)練數(shù)據(jù)量的匱乏直接導(dǎo)致機(jī)器學(xué)習(xí)模型過(guò)擬合或精度低。因此,基于云計(jì)算的機(jī)器學(xué)習(xí)技術(shù)應(yīng)運(yùn)而生,并得到了學(xué)術(shù)界、產(chǎn)業(yè)界和政府的廣泛關(guān)注。云計(jì)算是分布式計(jì)算、效用計(jì)算、并行計(jì)算和虛擬化等多種技術(shù)的融合演進(jìn)和躍升,用戶能夠以按需付費(fèi)的方式享受云平臺(tái)上無(wú)盡的存儲(chǔ)和計(jì)算資源。因而,用戶在云服務(wù)器的協(xié)助下進(jìn)行模型訓(xùn)練與優(yōu)化,不僅極大地降低了用戶端的計(jì)算開(kāi)銷和維護(hù)成本,而且可以實(shí)現(xiàn)分布式數(shù)據(jù)集的有效利用。然而,由于用戶數(shù)據(jù)中通常包含敏感信息且云服務(wù)器不完全可信,因此,基于云計(jì)算的機(jī)器學(xué)習(xí)技術(shù)不可避免地面臨一些安全問(wèn)題。首先,數(shù)據(jù)外包使得用戶失去了對(duì)其物理管控,如何保證訓(xùn)練過(guò)程中訓(xùn)練集數(shù)據(jù)隱私性和計(jì)算結(jié)果的可驗(yàn)證性,是面臨的安全挑戰(zhàn)之一。... 

【文章來(lái)源】：西安電子科技大學(xué)陜西省 211工程院校 教育部直屬院校

【文章頁(yè)數(shù)】：131 頁(yè)

【學(xué)位級(jí)別】：博士

【文章目錄】：
摘要
ABSTRACT
List of Abbreviations
Chapter 1 Introduction
    1.1 B ackground
    1.2 Related Work
    1.3 Our Contributions
    1.4 Organization
Chapter 2 Preliminaries
    2.1 Bilinear Pairings
    2.2 Paillier Encryption
    2.3 Publicly Verifiable Computation
    2.4 Summary
Chapter 3 Privacy-preserving and Publicly Verifiable Matrix Multiplication SchemeDeployed in Machine Learning
    3.1 Overview
    3.2 Problem Statement
        3.2.1 System Model
        3.2.2 Treat Model
    3.3 The Proposed Scheme
        3.3.1 Basic Components
        3.3.2 Main Idea
        3.3.3 The Concrete Construction
        3.3.4 Correctness
    3.4 Security Analysis
    3.5 Performance Analysis
        3.5.1 Efficiency Analysis
        3.5.2 Experimental Evaluation
    3.6 Summary
Chapter 4 Privacy-preserving and Verifiable SLP Training and Prediction Scheme
    4.1 Overview
    4.2 Problem Statement
        4.2.1 System Model
        4.2.2 Definition of Privacy-preserving Outsourcing Matrix Multiplication
        4.2.3 Security Model
    4.3 The Proposed Scheme
        4.3.1 Basic Components
        4.3.2 Main Idea
        4.3.3 The Concrete Construction
        4.3.4 Correctness
    4.4 Security Analysis
    4.5 Performance Analysis
        4.5.1 Efficiency Analysis
        4.5.2 Experimental Evaluation
    4.6 Summary
Chapter 5 Privacy-Preserving Federated Deep Learning Scheme
    5.1 Overview
    5.2 Problem Statement
        5.2.1 System Model
        5.2.2 Definitions of DeepPAR and DeepDPA
    5.3 The Proposed Scheme
        5.3.1 Basic Components
        5.3.2 Security Requirements
        5.3.3 Main Idea
        5.3.4 DeepPAR Based on Re-encryption
        5.3.5 DeepDPA Based on Group Key Management
    5.4 Security Analysis
    5.5 Performance Analysis
        5.5.1 Efficiency Analysis
        5.5.2 Experimental Evaluation
    5.6 Summary
Chapter 6 Privacy-Preserving and Verifiable Online Crowdsourcing Scheme Deployedin Machine Learning
    6.1 Overview
    6.2 Problem Statement
        6.2.1 System Model
        6.2.2 Definitions of PVOC
        6.2.3 Threat Model
        6.2.4 Design Goal
    6.3 The Proposed Scheme
        6.3.1 Basic Components
        6.3.2 Main Idea
        6.3.3 The Concrete Construction
    6.4 Security Analysis
    6.5 Performance Analysis
        6.5.1 Efficiency Analysis
        6.5.2 Experimental Evaluation
    6.6 Summary
Chapter 7 Conclusion and Future Work
    7.1 Conclusion
    7.2 Future Work
Bibliography
Acknowledgement
作者簡(jiǎn)介



本文編號(hào)：3456556