We’ll see you, anon
http://www.economist.com/news/science-and-technology/21660966-can-big-databases-be-kept-both-anonymous-and-useful-well-see-you-anon “A dilemma. People want perfect #privacy & all the benefits of openness.” Math to the rescue?
Good for an intro. on privacy & attacks
QT:{{”
This is a true dilemma. People want both perfect privacy and all the benefits of openness. But they cannot have both.
…
“While some level of anonymisation will remain part of any resolution of the dilemma, mathematics may change the overall equation. One approach that would shift the balance to the good is homomorphic encryption, whereby queries on an encrypted data set are themselves encrypted. The result of any inquiry is the same as the one that would have been obtained using a standard query on the unencrypted database, but the questioner never sets eyes on the data. Or there is secure multiparty computation, in which a database is divided among several repositories. Queries are thus divvied up so that no one need have access to the whole database.
These approaches are, on paper, absolute in their protections. But putting them to work on messy, real-world data is proving tricky. Another set of techniques called differential privacy seems further ahead. The idea behind it is to ensure results derived from a database would look the same whether a given individual’s data were in it or not. It works by adding a bit of noise to the data in a way that does not similarly fuzz out the statistical results.
…
America’s Census Bureau has used differential privacy in the past for gathering commuters’ data. Google is employing it at the moment as part of a project in which a browser plug-in gathers lots of data about a user’s software, all the while guaranteeing anonymity. Cynthia Dwork, a differential-privacy pioneer at Microsoft Research, suggests a more high-profile proving ground would be data sets—such as some of those involving automobile data or genomes—that have remained locked up because of privacy concerns.”
“}}