OpenData movement around the globe is demanding more access to information which lies locked in public or private servers. As recently reported by a McKinsey publication, this data has significant economic value, yet its release has potential to blatantly conflict with people privacy. Recent UK government inquires have shown concern from various parties about publication of anonymized databases, as there is concrete possibility of user identification by means of linkage attacks. Differential privacy stands out as a model that provides strong formal guarantees about the anonymity of the participants in a sanitized database. Only recent results demonstrated its applicability on real-life datasets, though. This paper covers such breakthrough discoveries, by reviewing applications of differential privacy for non-interactive publication of anonymized real-life datasets. Theory, utility and a data-aware comparison are discussed on a variety of principles and concrete applications.