An article by Dr. Gail Gilboa-Freedman her colleague under the title:
On the Behavioral Implications of Differential Privacy
Cite article
Gilboa-Freedman, G., & Smorodinsky, R. (2020). On the behavioral implications of differential privacy. Theoretical Computer Science, 841, 84-93.
Following the publication of the article "The Mathematics of Privacy: Behind the Scenes of Differential Privacy" we talked with Dr. Gail Gilboa-Freedman about the research:
"Differential privacy is commonly used in the computer science literature as a mathematical definition of privacy for the purpose of quantifying and limiting privacy loss. It produces an order of preference over the array of privacy-threatening mechanisms which, in turn, adhere to certain features of this order. We show that a set of five such features captures Distinguish the usual implications of prioritizing the alternatives in agreement with differential privacy. The model can also be applied to assess the appropriateness of differential privacy in different settings.
And in simpler words, imagine that you have data, and you want to use it for a good purpose without compromising anyone's privacy. This is where "differential privacy" comes in - it's like a super smart way to make sure your personal information stays safe. In this study, we dive in and try to understand and explain how this method works, why it's important, and find the best ways to use it. It's like putting on a superhero cape to protect your data"
Abstract
Differential privacy is commonly used in the computer science literature as a mathematical definition of privacy for the purpose of quantifying and bounding privacy loss. It induces a preference order over the set of privacy-jeopardizing mechanisms which, in turn, adhere to some properties of this order. We show that a set of five such properties uniquely captures the ordinal implications of prioritizing the alternatives in agreement with differential privacy. The model can also be applied to evaluate the appropriateness of differential privacy in different setting.
