Privacy Preserving Probabilistic Record Linkage Without Trusted Third Party

For the purpose of research, organizations often need to share and link data belonging to a single individual while protecting her privacy. This problem, referred to as privacy preserving record linkage (PPRL), has been investigated by researchers. Most PPRL works focus on deterministic linkages where the identifying attributes of two records must be equal in order to declare them to belong to the same individual. Moreover, most of these methods require the active participation of a trusted third party (TTP). If this TTP is compromised, it makes the data from all participating parties vulnerable to information leakage. The proposed work improves upon the existing methods in two ways. First, we propose a protocol which does not require two records to have an exact match on identifying attributes in order to be declared as belonging to the same individual. Second, we investigate probabilistic PPRL in the two-party setting without resorting to any TTP. We use Bloom filters for probabilistic matching and Yao's garbled circuit to perform the computation needed for the matching on encrypted data. To alleviate the computation and communication overhead of Yao's protocol, we leverage data blocking methods and optimize the computation. We provide a security proof of our method and experimentally evaluate the performance gained on large benchmark datasets.