PROJECT TITLE :

Searchable Encryption over Feature-Rich Data - 2018

ABSTRACT:

Storage services allow data homeowners to store their huge quantity of potentially sensitive knowledge, such as audios, pictures, and videos, on remote cloud servers in encrypted type. To enable retrieval of encrypted files of interest, searchable symmetric encryption (SSE) schemes are proposed. However, several schemes construct indexes based mostly on keyword-file pairs and target boolean expressions of tangible keyword matches. Moreover, most dynamic SSE schemes cannot achieve forward privacy and reveal unnecessary info when updating the encrypted databases. We tend to tackle the challenge of supporting large-scale similarity search over encrypted feature-rich multimedia information, by considering the search criteria as a high-dimensional feature vector rather than a keyword. Our solutions are designed on fastidiously-designed fuzzy Bloom filters which utilize locality sensitive hashing (LSH) to encode an index associating the file identifiers and feature vectors. Our schemes are proven to be secure against adaptively chosen question attack and forward private in the standard model. We have a tendency to have evaluated the performance of our theme on real-world high-dimensional datasets, and achieved a hunt quality of 99 % recall with solely some variety of hash tables for LSH. This shows that our index is compact and searching is not only efficient but conjointly correct.