Privacy-Enhanced Dependable and Searchable Storage in a Cloud-of-Clouds

• Autor(a) principal: Libório, João Paulo de Oliveira
• Data de Publicação: 2016
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10362/20619
• topic: Data storage clouds; Dependable cloud storage; Multi cloud architectures; Multi modal searchable encryption; RAM storage; Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática

In this dissertation we will propose a solution for a trustable and privacy-enhanced storage architecture based on a multi-cloud approach. The solution provides the necessary support for multi modal on-line searching operation on data that is always maintained encrypted on used cloud-services. We implemented a system prototype, conducting an experimental evaluation. Our results show that the proposal offers security and privacy guarantees, and provides efficient information retrieval capabilities without sacrificing precision and recall properties on the supported search operations. There is a constant increase in the demand of cloud services, particularly cloud-based storage services. These services are currently used by different applications as outsourced storage services, with some interesting advantages. Most personal and mobile applications also offer the user the choice to use the cloud to store their data, transparently and sometimes without entire user awareness and privacy-conditions, to overcome local storage limitations. Companies might also find that it is cheaper to outsource databases and keyvalue stores, instead of relying on storage solutions in private data-centers. This raises the concern about data privacy guarantees and data leakage danger. A cloud system administrator can easily access unprotected data and she/he could also forge, modify or delete data, violating privacy, integrity, availability and authenticity conditions. A possible solution to solve those problems would be to encrypt and add authenticity and integrity proofs in all data, before being sent to the cloud, and decrypting and verifying authenticity or integrity on data downloads. However this solution can be used only for backup purposes or when big data is not involved, and might not be very practical for online searching requirements over large amounts of cloud stored data that must be searched, accessed and retrieved in a dynamic way. Those solutions also impose high-latency and high amount of cloud inbound/outbound traffic, increasing the operational costs. Moreover, in the case of mobile or embedded devices, the power, computation and communication constraints cannot be ignored, since indexing, encrypting/decrypting and signing/verifying all data will be computationally expensive. To overcome the previous drawbacks, in this dissertation we propose a solution for a trustable and privacy-enhanced storage architecture based on a multi-cloud approach, providing privacy-enhanced, dependable and searchable support. Our solution provides the necessary support for dependable cloud storage and multi modal on-line searching operations over always-encrypted data in a cloud-of-clouds. We implemented a system prototype, conducting an experimental evaluation of the proposed solution, involving the use of conventional storage clouds, as well as, a high-speed in-memory cloud-storage backend. Our results show that the proposal offers the required dependability properties and privacy guarantees, providing efficient information retrieval capabilities without sacrificing precision and recall properties in the supported indexing and search operations.