Practical Secure Computation in the Client-Server Model

To compute something securely is to do so in a way that does not reveal (some of) the inputs, intermediate values, or outputs, to certain predetermined parties. For example, a hospital might outsource the computation of patients’ medical analyses to the cloud without the cloud provider being able to extract sensitive medical information. Researchers have proposed cryptographic protocols capable of performing secure computation for any function imaginable. However, there are still technical obstacles that hinder practical deployments of secure computation protocols. In this thesis, we identify four such impracticalities and propose techniques to address them.

A crucial building block that forms the basis of all protocols in this thesis is homomorphic encryption. Like ‘regular’ encryption it protects the encrypted values from being seen. However, it also allows one to perform computations on these encrypted values, without decrypting them. We distinguish between partially-homomorphic encryption schemes, which allow for some specific computations to be performed, and fully-homomorphic encryption schemes, which can perform any computation imaginable....