Double-Blinded Finder: A Two-Side Privacy-Preserving Approach for Finding Missing Children

Posting photos of suspected missing children on the street and posting them to social networks can help find missing children, but posting them to the Internet without protection may create privacy issues. In order to solve this problem, we propose Double-Blinded Finder, which is mainly used for low-dimensional multi-attribute matching of children’s face and blind face to find missing children and has high efficiency. To obtain enough knowledge for representing child faces, we build the Labeled Child Face in the Wild dataset, which contains 60K Internet images with 6K unique identities. We use this dataset to train a multitasking deep learning facial model, using a 128-dimensional feature vector and age and gender attributes to describe the child’s face. Due to the use of the face descriptor generation key, facial photos from the social network and facial information from the parents of the missing child are encrypted. In addition, we devise inner-production encryption to run blind face matching in the public cloud. In this manner, Double-Blinded Finder can provide efficient face matching while protecting the privacies of both sides: 1) Suspicious missing children in order to avoid human rights violations, 2) The real missing child is to retain the second victim. Experiments show that our system can achieve the actual performance of children’s face matching, and privacy leakage is negligible.