A bounded-noise mechanism for differential privacy
This work solves a key problem in differential privacy for researchers and practitioners by providing a bounded-noise mechanism that enhances privacy and accuracy in adaptive query settings.
The paper tackles the problem of answering multiple adaptive queries under differential privacy with bounded noise, achieving an asymptotically optimal mechanism that provides absolute error bounds and improves guarantees for adaptive data analysis, outperforming the Gaussian mechanism in standard settings.
We present an asymptotically optimal $(ε,δ)$ differentially private mechanism for answering multiple, adaptively asked, $Δ$-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm has a significant advantage that it adds independent bounded noise to each query, thus providing an absolute error bound. Additionally, we apply our algorithm in adaptive data analysis, obtaining an improved guarantee for answering multiple queries regarding some underlying distribution using a finite sample. Numerical computations show that the bounded-noise mechanism outperforms the Gaussian mechanism in many standard settings.