一種基于私有區(qū)塊鏈的信息保護(hù)預(yù)測(cè)模型研究
發(fā)布時(shí)間:2018-08-07 13:15
【摘要】:[目的/意義]預(yù)測(cè)建模是數(shù)據(jù)挖掘的基礎(chǔ)任務(wù)之一,當(dāng)前基于信息保護(hù)的預(yù)測(cè)模型大多建立在一個(gè)中心化的架構(gòu)之下,因而不可避免地存在一些安全性和魯棒性漏洞。因此嘗試一種新的、去中心化的預(yù)測(cè)建模方法,能夠兼具敏感信息保護(hù)和數(shù)據(jù)處理能力,無論對(duì)跨機(jī)構(gòu)互操作還是對(duì)國(guó)家層面的信息安全與共享服務(wù),均有重要的意義。[方法/過程]文章提出了一個(gè)新的預(yù)測(cè)模型架構(gòu)——模型鏈,將基于信息保護(hù)的在線機(jī)器學(xué)習(xí)與私有區(qū)塊鏈網(wǎng)絡(luò)技術(shù)相互整合,應(yīng)用交易元數(shù)據(jù)傳遞局部模型,并提出一種新的信息證明算法以確定在線學(xué)習(xí)進(jìn)程的執(zhí)行順序。[結(jié)果/結(jié)論]在模型鏈中,每個(gè)參與的站點(diǎn)都將有助于模型參數(shù)估計(jì),但無需透露己方的任何信息(即只有模型參數(shù)而沒有用戶數(shù)據(jù)在機(jī)構(gòu)間進(jìn)行交換);趨^(qū)塊鏈技術(shù)的預(yù)測(cè)建模能夠有效提高機(jī)構(gòu)間互操作性,同時(shí)規(guī)避了敏感信息泄露、數(shù)據(jù)處理需要中央服務(wù)器引導(dǎo)而產(chǎn)生的種種系統(tǒng)性、政策性風(fēng)險(xiǎn)。該方法將有助于支持全國(guó)范圍內(nèi)的信息共享服務(wù)的路線圖設(shè)計(jì)。[局限]模型鏈的技術(shù)實(shí)施還有待結(jié)合具體的網(wǎng)絡(luò)環(huán)境進(jìn)行評(píng)估,這也是開展后續(xù)研究的目標(biāo)。
[Abstract]:[objective / significance] Prediction modeling is one of the basic tasks of data mining. Currently, most of the prediction models based on information protection are based on a centralized framework, so there are inevitably some security and robustness vulnerabilities. Therefore, it is of great significance to try a new, decentralized predictive modeling method with both sensitive information protection and data processing capabilities, both for cross-agency interoperability and for information security and sharing services at the national level. [method / process] this paper proposes a new predictive model architecture, model chain, which integrates online machine learning based on information protection with private block chain network technology, and applies transaction metadata to transfer local model. A new information proof algorithm is proposed to determine the execution order of the online learning process. [results / conclusions] in the model chain, each participating site will contribute to the estimation of model parameters, but there is no need to disclose any information about the model (that is, only model parameters and no user data are exchanged between agencies). The prediction modeling based on block chain technology can effectively improve the interoperability between institutions and avoid the systematic and policy risks caused by the disclosure of sensitive information and the need for the central server to guide data processing. This approach will help support the roadmap design of information-sharing services across the country. The technical implementation of the model chain needs to be evaluated in the light of the specific network environment, which is also the goal of further research.
【作者單位】: 武漢大學(xué)信息管理學(xué)院;武漢大學(xué)計(jì)算機(jī)學(xué)院;
【基金】:國(guó)家自然科學(xué)基金項(xiàng)目“融合情境的移動(dòng)閱讀推薦系統(tǒng)研究”(項(xiàng)目編號(hào):71373192),國(guó)家自然科學(xué)基金項(xiàng)目“面向移動(dòng)終端的情境隱私保護(hù)理論與方法研究”(項(xiàng)目編號(hào):61572380)和國(guó)家自然科學(xué)基金面上項(xiàng)目“無線Mesh網(wǎng)絡(luò)中跨層安全關(guān)鍵技術(shù)研究”(項(xiàng)目編號(hào):61272451)的部分成果
【分類號(hào)】:G203
本文編號(hào):2170136
[Abstract]:[objective / significance] Prediction modeling is one of the basic tasks of data mining. Currently, most of the prediction models based on information protection are based on a centralized framework, so there are inevitably some security and robustness vulnerabilities. Therefore, it is of great significance to try a new, decentralized predictive modeling method with both sensitive information protection and data processing capabilities, both for cross-agency interoperability and for information security and sharing services at the national level. [method / process] this paper proposes a new predictive model architecture, model chain, which integrates online machine learning based on information protection with private block chain network technology, and applies transaction metadata to transfer local model. A new information proof algorithm is proposed to determine the execution order of the online learning process. [results / conclusions] in the model chain, each participating site will contribute to the estimation of model parameters, but there is no need to disclose any information about the model (that is, only model parameters and no user data are exchanged between agencies). The prediction modeling based on block chain technology can effectively improve the interoperability between institutions and avoid the systematic and policy risks caused by the disclosure of sensitive information and the need for the central server to guide data processing. This approach will help support the roadmap design of information-sharing services across the country. The technical implementation of the model chain needs to be evaluated in the light of the specific network environment, which is also the goal of further research.
【作者單位】: 武漢大學(xué)信息管理學(xué)院;武漢大學(xué)計(jì)算機(jī)學(xué)院;
【基金】:國(guó)家自然科學(xué)基金項(xiàng)目“融合情境的移動(dòng)閱讀推薦系統(tǒng)研究”(項(xiàng)目編號(hào):71373192),國(guó)家自然科學(xué)基金項(xiàng)目“面向移動(dòng)終端的情境隱私保護(hù)理論與方法研究”(項(xiàng)目編號(hào):61572380)和國(guó)家自然科學(xué)基金面上項(xiàng)目“無線Mesh網(wǎng)絡(luò)中跨層安全關(guān)鍵技術(shù)研究”(項(xiàng)目編號(hào):61272451)的部分成果
【分類號(hào)】:G203
【相似文獻(xiàn)】
相關(guān)期刊論文 前3條
1 鄧趕生;;個(gè)人信息保護(hù)之立法理念研究——在信息保護(hù)與信息自由之間[J];法制博覽(中旬刊);2013年01期
2 邢國(guó)春;陳星霖;;一種新型網(wǎng)絡(luò)入侵檢測(cè)系統(tǒng)對(duì)信息保護(hù)的預(yù)取模型[J];情報(bào)科學(xué);2012年06期
3 ;數(shù)字[J];傳媒;2013年01期
相關(guān)重要報(bào)紙文章 前2條
1 劉德良 北京師范大學(xué)教授 亞太網(wǎng)絡(luò)法律研究中心主任;讓網(wǎng)絡(luò)信息保護(hù)更具可操作性[N];中國(guó)紀(jì)檢監(jiān)察報(bào);2013年
2 石鷹;信息保護(hù)構(gòu)建“公民本位”社會(huì)[N];經(jīng)濟(jì)視點(diǎn)報(bào);2008年
,本文編號(hào):2170136
本文鏈接:http://sikaile.net/xinwenchuanbolunwen/2170136.html
最近更新
教材專著