Biblio

Massive images are being shared via a variety of ways, such as social networking. The rich content of images raise a serious concern for privacy. A great number of efforts have been devoted to designing mechanisms for privacy protection based on the assumption that the privacy is well defined. However, in practice, given a collection of images it is usually nontrivial to decide which parts of images should be protected, since the sensitivity of objects is context-dependent and user-dependent. To meet personalized privacy requirements of different users, we propose a system IEye to automatically detect private parts of images based on both common knowledge and personal knowledge. Specifically, for each user's images, multi-layered semantic graphs are constructed as feature representations of his/her images and a rule set is learned from those graphs, which describes his/her personalized privacy. In addition, an optimization algorithm is proposed to protect the user's privacy as well as minimize the loss of utility. We conduct experiments on two datasets, the results verify the effectiveness of our design to detect and protect personalized image privacy.

Recently, many methods have been proposed to prevent privacy leakage in record linkage by encoding record pair data into another anonymous space. Nevertheless, they cannot perform well in some circumstances due to high computational complexities, low privacy guarantees or loss of data utility. In this paper, we propose distance-aware encoding mechanisms to compare numerical values in the anonymous space. We first embed numerical values into Hamming space by a low-computational encoding algorithm with randomized bit vector. To provide rigorous privacy guarantees, we use the random response based on differential privacy to keep global indistinguishability of original data and use Laplace noises via pufferfish mechanism to provide local indistinguishability. Besides, we provide an approach for embedding and privacy-related parameters selection to improve data utility. Experiments on datasets from different data distributions and application contexts validate that our approaches can be used efficiently in privacy-preserving record linkage tasks compared with previous works and have excellent performance even under very small privacy budgets.