中文词义密文模糊搜索算法研究  

Research on fuzzy search algorithm of Chinese word meaning ciphertext

作　　者：张志红 付钰[1] 付伟[1] ZHANG Zhihong;FU Yu;FU Wei(Dept.of Information Security,Naval Univ.of Engineering,Wuhan 430033,China)

机构地区：[1]海军工程大学信息安全系,武汉430033

出　　处：《海军工程大学学报》2024年第6期38-45,共8页Journal of Naval University of Engineering

基　　金：国家自然科学基金资助项目(62276273);海军工程大学自主立项基金资助项目(2022508040)。

摘　　要：为解决云存储中密文数据的语义模糊搜索问题,设计了一种面向中文词义的云存储密文模糊搜索算法。利用Word2vec轻量级神经网络将词语转化为结构化向量,并进行语汇的相似度衡量,扩展关键词的中文近义词集;以布隆过滤器为基础,利用位置敏感哈希函数构造文件索引与搜索陷门,实现对关键词的安全存储和对多关键词的检索支持;在位置敏感哈希函数映射后再结合文件ID计算二轮哈希值进行混淆,并在文件加密过程中引入MD5值,实现了文件完整性验证。理论分析和仿真实验证明:所设计的密文模糊搜索算法能够实现基于中文词义的多关键词密文模糊搜索。In order to solve the semantic fuzzy search problem of ciphertext data in cloud storage,a fuzzy search algorithm for Chinese word sense in cloud storage ciphertext was designed.The Word2vec lightweight neural network was used to transform the words into structured vectors,and the similarity of the words was measured to expand the set of Chinese synonyms of the keywords.And then,based on the Bloom filter,the location-sensitive hash function was used to construct the file index and search trapdoor,so as to realize the secure storage of keywords and the retrieval support for multi-keywords.After the location sensitive hash function mapping,the file ID was combined to calculate the two rounds of hash value for confusion and the MD5 value was introduced in the file encryption process to realize the file integrity verification.The oretical analysis and simulation results show that the designed ciphertext fuzzy search algorithm can realize multi-keyword ciphertext fuzzy search based on Chinese word sense.

关 键 词：密文检索 布隆过滤器 位置敏感哈希函数 Word2vec 语义相似度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]