Harvard University Privacy Tools Project – “…Differential privacy is a rigorous mathematical definition of privacy. In the simplest setting, consider an algorithm that analyzes a dataset and computes statistics about it (such as the data’s mean, variance, median, mode, etc.). Such an algorithm is said to be differentially private if by looking at the output, one cannot tell whether any individual’s data was included in the original dataset or not. In other words, the guarantee of a differentially private algorithm is that its behavior hardly changes when a single individual joins or leaves the dataset — anything the algorithm might output on a database containing some individual’s information is almost as likely to have come from a database without that individual’s information. Most notably, this guarantee holds for any individual and any dataset. Therefore, regardless of how eccentric any single individual’s details are, and regardless of the details of anyone else in the database, the guarantee of differential privacy still holds. This gives a formal guarantee that individual-level information about participants in the database is not leaked. The definition of differential privacy emerged from a long line of work applying algorithmic ideas to the study of privacy (Dinur and Nissim `03; Dwork and Nissim `04; Blum, Dwork, McSherry, and Nissim `05), culminating with work of Dwork, McSherry, Nissim, and Smith `06. See our educational materials for more detail about the formal definition of differential privacy and its semantic guarantees…”