“…For a privacy parameter α ∈ [0, ∞], any non-interactive privacy mechanism is said to be an α-locally differentially private mechanism if the con- , 2018;Berrett and Butucea, 2019;Butucea et al, 2020;Berrett et al, 2021;Györfi and Kroll, 2023). In order to define the privatized data, we first choose a closed Euclidean ball B = {x ∈ R d : x ≤ r} of radius r > 0 centred at the origin.…”