"Differential privacy is a framework for privately releasing summaries of a database. Previous work has focused mainly on methods for which the output is a finite dimensional vector, or an element of some discrete set. We develop methods for releasing functions while preserving differential privacy. Specifically, we show that adding an appropriate Gaussian process to the function of interest yields differential privacy. When the functions lie in the same RKHS as the Gaussian process, then the correct noise level is established by measuring the "sensitivity" of the function in the RKHS norm. As examples we consider kernel density estimation, kernel support vector machines, and functions in reproducing kernel Hilbert spaces."

Cf. http://www.theonion.com/content/node/57311

Amusing and thoughtful, but of course it's going to be as quaint looking in 2061 as 1911's vision of 1961.

"Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). ... a new method, objective perturbation, for privacy-preserving machine learning algorithm design ... perturbing the objective function before optimizing ...our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. ... a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees ... encouraging results from ... performance on real demographic and benchmark data sets... objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance."