δ-Presence without Complete World Knowledge

48 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Federated Learning: Challenges, Methods, and Future Directions (2019, background): “Despite the fact that differential privacy is the de facto metric for privacy in machine learning, there are many other privacy definitions, such as k-anonymity [15] and d-presence [34], which may be applicable to different learning problems.”
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks (2017, background): “(Nergiz and Clifton, 2010) Presence disclosure for medGAN happens when a powerful attacker, one who already possesses the complete records of a set of patients P , can determine whether anyone from P are in the training set by observing the generated patient records.”
How Much Is Enough? Choosing ε for Differential Privacy (2011, background): “This may be an inherent problem with protecting privacy; δ-presence [14] faces the same issue (although an approximation based on univariate statistics is given in [13].”