This paper develops robust estimation algorithms for state-space models that are subject to bounded parametric uncertainties. Compared with existing robust filters, the new filters perform data regulaarization rather than de-regularization and they do not require existence conditions. The resulting filter structures also turn out to be similar to various (time- and measurement-update, prediction, and information) forms of the Kalman filter, albeit ones that operate on corrected parameters rather than on the given nominal parameters.