Title: Privacy-Preserving Content-Based Image Retrieval in the Cloud
By: Bernardo Ferreira (DI-FCT-UNL)
Host: Computer Systems
Abstract:
Storage requirements for visual data have been increasing in recent years, following the emergence of many new highly interactive multimedia services and applications for both personal and corporate use. This has been a key driving factor for the adoption of cloud-based data outsourcing solutions. However, outsourcing data storage to the Cloud also leads to new challenges that must be carefully addressed, especially regarding privacy. In this paper we propose a secure framework for outsourced privacy-preserving storage and retrieval in large image repositories. Our proposal is based on IES-CBIR, a novel Image Encryption Scheme that displays Content-Based Image Retrieval properties. Our solution enables both encrypted storage and searching using CBIR queries while preserving privacy. We have built a prototype of the proposed framework, formally analyzed and proven its security properties, and experimentally evaluated its performance and precision. Our results show that IES-CBIR is provably secure, allows more efficient operations than existing proposals, both in terms of time and space complexity, and enables more reliable practical application scenarios.
This presentation is based on a SRDS’15 paper.
Bio:
Bernardo Ferreira is a Ph.D. student at Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa (FCT/UNL) and a junior researcher at the NOVASYS group of the NOVA LINCS research center. He is advised by Professor Henrique Domingos (FCT/UNL) and his dissertation is on the topics of Cloud security and dependability solutions, with special emphasis on the study of data privacy, reliability and availability services, as well as on property-preserving encryption algorithms and their application in performing computations over encrypted data. He holds a M.Sc. in Computer Science from FCT/UNL and before starting his Ph.D. he worked as a Software Developer for PT Inovação.