Approximate nearest neighbors search with security and privacy requirements

Participants : Benjamin Mathon, Laurent Amsaleg, Teddy Furon.

In collaboration with Julien Bringer, Morpho, France.

A privacy-preserving framework for large-scale content-based information retrieval

Participants : Ewa Kijak, Laurent Amsaleg, Teddy Furon.

In close cooperation with Stéphane Marchand-Maillet, Li Weng and April Morton, University of Geneva, Switzerland.

We propose a privacy protection framework for large-scale content-based information retrieval. It offers two layers of protection. First, robust hash values are used as queries instead of original content or features. Second, the client can choose to omit certain bits in a hash value to further increase the ambiguity for the server. Due to the reduced information, it is computationally difficult for the server to know the client's interest. The server has to return the hash values of all possible candidates to the client. The client performs a search within the candidate list to find the best match. Since only hash values are exchanged between the client and the server, the privacy of both parties is protected.

We introduce the concept of tunable privacy, where the privacy protection level can be adjusted according to a policy. It is realized through hash-based piece-wise inverted indexing. The idea is to divide a feature vector into pieces and index each piece with a sub-hash value. Each sub-hash value is associated with an inverted index list.

The framework has been extensively tested using a large image database. We have evaluated both retrieval performance and privacy-preserving performance for a particular content identification application. Two different constructions of robust hash algorithms are used. One is based on random projections; the other is based on the discrete wavelet transform. Both algorithms exhibit satisfactory performance in comparison with state-of-the-art reference schemes. The results show that the privacy enhancement slightly improves the retrieval performance.

We consider the majority voting attack for estimating the query category and ID. Experiment results show that this attack is a threat when there are near-duplicates, but the success rate decreases with the number of omitted bits and the number of distinct items.

Privacy preserving data aggregation and service personalization using highly-scalable indexing techniques

Participants : Raghavendran Balu, Laurent Amsaleg, Hervé Jégou, Teddy Furon.

In collaboration with Armen Aghasaryan, Dimitre Davidov and Makram Bouzid, Alcatel-Lucent, and Sébastien Gambs, Inria/CIDRE, in the framework of the Alcaltel-Lucent / Inria common Lab.

A challenging approach to the problem of privacy preserving data aggregation and service personalization has recently been proposed in Bell Labs, which introduces a privacy-preserving intermediation layer between end-users and service providers. It uses a distributed variant of a Locality Sensitive Hashing (LSH) techniques of doing scalable nearest-neighbor search, adapted in a novel way, to discover similar users while preserving their privacy. This approach faces however several important challenges that will be targeted in the scope of this collaboration. The challenges are: