Secure Shape Recognition

Recent advances in technology provided a suitable environment in which people can benefit from online services in their daily lives. Despite several advantages, online services also constitute serious privacy risks for their users as the main input to their algorithms are privacy sensitive data such as demographic information, shopping patterns, medical records, etc. While traditional security mechanisms can eliminate a number of attacks from outside, these mechanisms can not protect the privacy of the users as the service provider itself constitutes the biggest potential risk.

To protect the privacy of users in multimedia applications, we focus on keeping the privacy-sensitive data safe by means of encryption during processing. This approach eliminates the risk of possible privacy abuse as the sensitive data is only available to the owner but no other party. To illustrate this idea, we designed a "Secure Shape Recognition" system, in which a private query via a mobile phone can be realized without revealing the query to the service provider.

Note that, once encrypted, the structure in data is destroyed as a consequence of the encryption procedure and thus we need appropriate tools to process encrypted data. Therefore, the underlying protocol relies on a number of cryptographic tools such as homomorphic encryption schemes and multiparty computation (MPC) techniques to realize privacy-preserving multimedia applications.