Privacy-preserving Research in Medicine – PMR

Given the growing awareness of privacy risks of data processing, there is an increasing interest in privacy-preserving learning. However, shortcomings in the state of the art limit the applicability of the privacy-preserving learning paradigm. First, most approaches assume too optimistically a honest-but-curious setting. Second, most approaches consider one learning task in isolation, not accounting for the context where querying is a recurring activity. We will investigate new algorithms and models that address these shortcomings. Among others, we will propose robust algorithms taking into account specifics of the medical application domains we consider, using refined notions of privacy and prior domain knwoledge, and reasoning about privacy over the complete application rather than isolated steps.