Secure and Large image databases indexing – SecuLar

Since their invention, content based image retrieval systems (CBRS) and biometric systems have evolved separately. This is due to the fact that they originate from different research and industrial communities. The Basic Research project described in this application, called SecuLar, groups researchers from both communities who have observed that both type of systems have indeed a lot in common in terms of goals and technological blocks. These techniques are used, however, in quite different settings possibly explaining the gap between the two. The people involved in this SecuLar project believe that what is specific to each family of approach can now benefit the other for the two following fundamental reasons.

Biometrics needs scale. The size of biometric databases quickly increases. It grows in terms of the number of records kept in the database. It also grows in terms of the size of each record as larger biometric templates maintain high quality recognition. The amount of data becomes large enough to require powerful indexing techniques. CBRS are good at this as they allow ultra fast searches of nearest neighbours in huge datasets. But porting these techniques to a biometric context is far from being easy. Biometric databases are typically protected to enforce confidentiality and privacy as security is paramount. Indexing biometric data is thus difficult because the techniques enforcing security in biometrics conflict with the technique bringing efficiency to database searches. No biometric system can today cope with both all the privacy and security constraints and the scale at which they should work in the real world for new applications. This is especially the case with face detection and recognition that today securely work at small scale. Indexing large amount of faces while preserving privacy, confidentiality and search speed is not yet possible. SecuLar aims at pushing one step further the understanding of securely indexing large amount of high-dimensional data. We plan to revisit state-of-art indexing techniques to cope with the complex metrics used in face recognition as well as the special nature of biometric datasets. Here, we are convinced that CBRS technologies will help biometrics.

CBRS need security and privacy. We witness a new use of CBRS these days. CBRS become the main ‘multimedia security’ technology to enforce copyright laws (content monetization) or to spot illegal contents (detection of copies, paedophile images, ...) over the Internet. The state-of-the-art CBRS are robust and can handle collections of millions of images. However, they were not designed with privacy, confidentiality and security in mind. This comes in serious conflict with their use in these new security-oriented applications. Privacy is endangered due to information leaks when correlating users, queries and the contents stored-in-the-clear in the database. It is especially the case of images containing faces which are so popular in social networks. Biometrics systems have long relied on protection techniques and anonymization processes that have never been used in the context of CBRS. Here, we plan to understand how biometrics related techniques can help increasing the security levels of CBIRS while not degrading their performance.

SecuLar is a very challenging project because it asks to merge various expertises coming from domains as diverse as signal and image processing, databases, cryptography, and privacy management. Secular is composed of three main partners (Inria, GREYC, and Morpho) whose expertises complementarily cover all these fields, yet never gathered together before. This will be achieved under the supervision of a fourth partner, Prof. G. Cohen of Telecom ParisTech, who is an expert in information theoretical security.