The Limits of Two-Party Differential Privacy

By Andrew McGregor, Ilya Mironov, Toniann Pitassi, Omer Reingold, Kunal Talwar, Salil P. Vadhan. 2010

192 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Privacy & Security

How researchers see this paper

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

In Artificial Intelligence

In Privacy & Security

Citations in the corpus

On Distributed Differential Privacy and Counting Distinct Elements (2020, methodology): “McGregor et al. [33] studied the DP two-party and proved an interesting separation of Ω ε ( n ) between the global sensitivity and ε -DP protocol in this model.”
The power of synergy in differential privacy: Combining a small curator with local randomizers (2019, background): “The local model agents receive enough information to recover all secrets, but doing so would breach privacy (as implied by [46]).”
Personalized and Private Peer-to-Peer Machine Learning (2017, background): “The private multi-party setting, in which sensitive datasets are distributed across multiple data owners, is known to be harder (McGregor et al., 2010) and has been less studied in spite of its relevance for many applications.”
Rényi Differential Privacy (2017, background): “The IND-CDP notion allows much more accurate functionalities in the two-party setting [12]; in the traditional client-server setup there is a natural class of functionalities where the gap between IND-CDP and ( , δ)-DP is minimal [13], and there are (contrived) examples where the computational relax”
Local, Private, Efficient Protocols for Succinct Histograms (2015, methodology): “We also adapt a result of McGregor et al (2010) to the local setting.”
The Power of Linear Reconstruction Attacks (2012, background): “This is already perhaps surprising, since many of the above releases (likeM -estimators) are obtained by solving highly nonlinear formulations.”
When is memorization of irrelevant training data necessary for high-accuracy learning? (2020, background): “More formally, it is known that differential privacy implies a bound on the mutual information I(X;M) [27, 17, 34, 10].”