Timezone: »

 
Poster
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
Badih Ghazi · Ravi Kumar · Pasin Manurangsi · Rasmus Pagh · Amer Sinha

Thu Jul 22 09:00 PM -- 11:00 PM (PDT) @ Virtual
in Poster Session 6 »

The shuffle model of differential privacy has attracted attention in the literature due to it being a middle ground between the well-studied central and local models. In this work, we study the problem of summing (aggregating) real numbers or integers, a basic primitive in numerous machine learning tasks, in the shuffle model. We give a protocol achieving error arbitrarily close to that of the (Discrete) Laplace mechanism in central differential privacy, while each user only sends 1 + o(1) short messages in expectation.

Keywords: Privacy, Anonymity, and Security · Social Aspects of Machine Learning
[ Slides] 

Author Information

Badih Ghazi (Google)
Ravi Kumar (Google)
Pasin Manurangsi (Google Research)
Rasmus Pagh (University of Copenhagen)
Amer Sinha (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors