|Home \ Prototypes \ Prototype Page||Login|
A Privacy-Preserving Prototype for Content-Based Image Retrieval in the Cloud
Storage requirements for visual data has been increasing in recent years, following the emergence of many new 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, specially regarding privacy. This prototype demonstrates how to implement a secure and privacy-preserving framework for the outsourced storage and retrieval of large image repositories. The prototype is based on a novel cryptographic scheme, named IES-CBIR, specifically designed for media image data. The prototype also presents an implementation of IES-CBIR, enabling both the encrypted storage and searching using Content Based Image Retrieval (CBIR) and while preserving privacy. An experimental evaluation of the prototype shows that it allows more efficient operations than existing proposals, both in terms of time and space complexity for the different system operations it provides.
Date: November, 2014
Authors: Bernardo Ferreira, Henrique João Domingos, João Leitão