基于混合云架构的深度语义密文检索

Deep semantic ciphertext retrieval based on hybrid cloud architecture

针对传统的云环境下密文检索方案基于统计学模型来生成文件向量和检索向量,并没有考虑文件和请求的深层次语义信息,提出一种基于混合云架构的深层次语义密文检索模型。通过私有云联邦学习神经网络模型构建向量生成模型,通过公有云存储密文数据。另外,提出密倒排索引表来存放文件向量,在公有云的检索过程中,保证检索信息不被泄露的情况下提高检索的效率。对真实数据集的分析和实验表明,提出的方案在安全性和搜索效率方面都优于目前同类型的密文检索方案。

Aiming at the traditional ciphertext retrieval scheme in cloud environment,which generates file vectors and retrieval vectors based on statistical model,and does not consider the deep-seated semantic information of files and requests,this paper proposed a deep-seated semantic ciphertext retrieval model based on hybrid cloud architecture.It constructed the vector gene-ration model through the private cloud federated learning neural network model,and stored the ciphertext data through the public cloud.In addition,this paper proposed a secret inverted index table to store file vectors,so as to improve the efficiency of retrieval without ensuring that the retrieval information was not leaked in the retrieval process of public cloud.The analysis and experiments on real data sets show that this scheme is better than the current ciphertext retrieval schemes of the same type in terms of security and search efficiency.