基于BTM主题模型的对称可搜索加密方案

为了实现基于语义的密文检索,提高密文检索的准确率和效率,本文提出了一种基于biterm主题模型(biterm topic model,BTM)的多关键词可排序对称可搜索加密方案(BTM-MRSE).通过主题模型对关键词和文档之间的潜在语义进行建模,用户利用查询关键词的概率分布作为检索陷门,根据查询关键词与文档之间的语义相关性得分来获得最相关的文档.本方案将密文检索中的特定关键词替换为基于语义的主题,实现了关键词和文档标识符的分离,从而增强了文档关键词与查询关键词的隐私保护.为了减小索引规模,我们提出两层索引结构,利用平衡二叉树构造关键词-主题安全索引,结合倒排索引构造主题-文档安全索引.一方面,主题模型减小了索引节点中向量的维数,从而提高了检索效率,同时基于平衡二叉树的二级索引机制也进一步改善了密文检索效率.安全性分析证明了所提方案是安全有效的,同时利用真实数据集进行实验对比,表明本方案的密文检索准确率和效率都有极大提升.

BTM Topic Model Based Searchable Symmetric Encryption

In order to enable semantic-based ciphertext retrieval and improve the accuracy and efficiency of searchable symmetric encryption,an efficient multi-keyword searchable symmetric encryption scheme is proposed based on biterm topic model(BTM-MRSE).The topic-based model is used to model the underlying semantics between keywords and documents.When querying data,a user uses the probability distribution of the queried keyword as a searching trapdoor to obtain the most relevant document according to the semantic relevance score between the queried keyword and the document.The proposed scheme replaces the specific keywords in the ciphertext search with a relevant topic,separates the keywords and document identifiers,and improves the privacy protection of keywords and queries.In order to reduce the size of the indexes,a two-layer index structure is proposed,a balanced binary tree is used to construct a keyword-topic secure index,and a topic-document secure index is constructed by combining an inverted index.On the one hand,the topic-based model reduces the dimensionality of the vector in the index node,which improves the search efficiency.On the other hand,the two-layer index mechanism based on the balanced binary tree further improves the ciphertext retrieval efficiency.The security analysis shows that the proposed scheme is secure and effective,and the experimental results on real datasets show that the accuracy and efficiency of the proposed scheme are greatly improved compared to other schemes.