Distributed Differential Privacy By Sampling
This work addresses privacy preservation in distributed systems for data analysts, but it appears incremental as it builds upon existing mechanisms like randomized response.
The paper tackles the problem of achieving distributed differential privacy using only sampling, showing that their mechanism maintains constant utility without degradation from variance and results in smaller privacy leakage compared to randomized response.
In this paper, we describe our approach to achieve distributed differential privacy by sampling alone. Our mechanism works in the semi-honest setting (honest-but-curious whereby aggregators attempt to peek at the data though follow the protocol). We show that the utility remains constant and does not degrade due to the variance as compared to the randomized response mechanism. In addition, we show smaller privacy leakage as compared to the randomized response mechanism.