摘要：

数据持有性审计是保证云存储数据完整性的重要方法,但并发更新操作会导致审计系统效率大幅降低。为此,提出一种支持并发更新的云存储数据持有性审计方法。通过改进Merkle哈希树(MHT)结构,将多个请求更新MHT中间节点的过程延后执行,生成更新状态树,分离出多个叶子节点更新路径并合并执行,从而避免重复节点更新,降低云存储数据完整性验证系统的更新成本。形式化分析及实验结果表明,该方法能减少更新MHT节点数,提高云存储数据持有性审计的更新效率。

关键词: 并发更新, 数据持有性证明, 数据完整性, 云存储, 数据安全

Abstract:

Audit of data possession is the key technique of ensuring the cloud data integrity,but the concurrent update operation makes the audit system efficiency dramatically decreased.Aiming at this problem,this paper proposes an audit method of cloud storage data possession supporting concurrent update.By improving Merkle Hash Tree(MHT) structure,it makes multiple updated requests of MHT intermediate node delay execution and generates updated state tree.It separates multiple leaf nodes and combines them to execute,which can significantly eliminate duplicate nodes in MHT,and effectively reduce the update cost of cloud storage data integrity audit system.Both formal analysis and the experimental results indicate that the proposed method can efficiently reduce the number of updating MHT nodes,and improve the update efficiency for the audit of cloud storage data possession.

Key words: concurrent update, Provable Data Possession(PDP);data integrity;cloud storage;data security

中图分类号: 

• TP391