Low Influence, Utility, and Independence in Differential Privacy: A Curious Case of 3 2

by   Rafael G. L. D'Oliveira, et al.

We study the relationship between randomized low influence functions and differentially private mechanisms. Our main aim is to formally determine whether differentially private mechanisms are low influence and whether low influence randomized functions can be differentially private. We show that differential privacy does not necessarily imply low influence in a formal sense. However, low influence implies approximate differential privacy. These results hold for both independent and non-independent randomized mechanisms, where an important instance of the former is the widely-used additive noise techniques in the differential privacy literature. Our study also reveals the interesting dynamics between utility, low influence, and independence of a differentially private mechanism. As the name of this paper suggests, we show that any two such features are simultaneously possible. However, in order to have a differentially private mechanism that has both utility and low influence, even under a very mild utility condition, one has to employ non-independent mechanisms.


page 1

page 2

page 3

page 4


DPGen: Automated Program Synthesis for Differential Privacy

Differential privacy has become a de facto standard for releasing data i...

Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy

Deployment of deep learning in different fields and industries is growin...

Subspace Differential Privacy

Many data applications have certain invariant constraints due to practic...

On Dynamic Noise Influence in Differentially Private Learning

Protecting privacy in learning while maintaining the model performance h...

Differentially Private Condorcet Voting

Designing private voting rules is an important and pressing problem for ...

Differentially Private Median Forests for Regression and Classification

Random forests are a popular method for classification and regression du...

A Differentially Private Game Theoretic Approach for Deceiving Cyber Adversaries

Cyber deception is one of the key approaches used to mislead attackers b...

Please sign up or login with your details

Forgot password? Click here to reset