Paper Info
Title
Privacy-preserving personalized search over encrypted cloud data supporting multi-keyword ranking
Abstract
Cloud computing is emerging as a revolutionary computing paradigm which provides a flexible and economic strategy for data management and resource sharing. Security and privacy become major concerns in the cloud scenario, for which Searchable Encryption (SE) technology is proposed to support efficient keyword based queries and retrieval of encrypted data. However, the absence of personalized search is still a typical shortage in existing SE schemes. In this paper, we focus on addressing personalized search over encrypted cloud data and propose a Privacy-preserving Personalized Search over Encrypted Cloud Data Supporting Multi-keyword Ranking(PPSE) scheme that supports Top-k retrieval in stringent privacy requirements. For the first time, we formulate the privacy issue and design goals for personalized search in SE. We introduce the Open Directory Project to construct a formal model for integrating preferential ranking with keyword search reasonably and automatically, which can help eliminate the ambiguity of any two search requests. In PPSE, we employ the vector space model and the secure kNN scheme to guarantee sufficient search accuracy and privacy protection. The tf-idf weight and the preference weight help to ensure that the search result will faithfully respect the user's interest. As a result, thorough security analysis and performance evaluation on experiments performed on the real-world dataset demonstrate that the PPSE scheme indeed accords with our proposed design goals.
Year
DOI
Venue
2014
10.1109/WCSP.2014.6992161
WCSP
Keywords
Field
DocType
keyword search,tf-idf weight,vector space model,se technology,data privacy,real-world dataset,cryptography,keyword-based encrypted data query,preference weight,search request ambiguity elimination,top-k retrieval,open directory project,flexible-economic resource sharing strategy,secure knn scheme,ppse scheme,search accuracy,preferential ranking integration,multi-keyword ranking,performance evaluation,security analysis,user interest,cloud computing,searchable encryption,privacy-preserving personalized search,keyword-based encrypted data retrieval,privacy protection,flexible-economic data management strategy,formal model,query processing,encrypted cloud data supporting multikeyword ranking,personalized search,dictionaries,servers,indexes,vectors
Personalized search,Ranking,Information retrieval,Cryptography,Computer science,Encryption,Vector space model,Information privacy,Data management,Cloud computing
Conference
Citations 
PageRank 
References 
3
0.43
11
Authors
4
Name
Order
Citations
PageRank
Ruihui Zhao130.43
Li Hongwei253561.38
Yi Yang3312.66
Yu Liang42112.01