The Research On Hierarchical Dynamic Attribute-based Keyword Search In Cloud Computing

Due to its fast deployment and scalability etc,cloud computing has become a significant technology trend.More and more organizations and enterprises can achieve great flexibility at a low price by outsourcing their data and query services to the cloud.Since the cloud is not totally trusted,existing research suggests encrypting data before outsourcing to preserve user privacy.Therefore,searchable encryption was proposed to enable a user to retrieve data of interest while keeping user privacy from the cloud.The existing attribute-based keyword search(ABKS)scheme achieves a fine-grained search authorization,which allows a data owner to control the search of the outsourced encrypted data according to an access policy.However,the ABKS scheme never considers the problem of a dynamic access policy for keywords.Moreover,since the ABKS scheme uses a monotonous tree-access structure,the cost of encryption for the data owner is directly proportional to the number of attributes in the access policy.For a system with a large number of users and attributes,the cost for encryption may be to large.Based on the above analyses,the key contributes of this paper are as follows:First,to achieve the update of access policy efficiently,a dynamic attribute-based keyword search(DABKS)scheme is proposed.The DABKS scheme,which incorporates proxy re-encryption technology and a secret sharing scheme into ABKS,allows the data owner to delegate policy updating operations to the cloud,takes full advantage of cloud resources.It not only achieves a dynamic search authorization,but also reduce the computation and communication costs of data owners.Next,to improve the encryption performance of data owner,a hierarchical attribute-based keyword search(HABKS)scheme is proposed.By building a hierarchical tree for attributes in the system,the association between the attributes is established.The HABKS scheme encrypts keywords with a small number of specific attributes at a lower level,greatly reducing the number of attributes in access policy and improving the encryption performance of data owner.The HABKS scheme encode each attribute node with the positive-negative depth-first coding.By virtue of the forward derivation function,the users associated with the generalized attributes at a higher level can retrieve files containing the target keyword which is encrypted with the specific attributes at lower level.Finally,we completed the above work,and conducted experiments on real data sets to validate the effectiveness and efficiency of our proposed scheme.