Struct MaxDivergence

pub struct MaxDivergence;

Privacy measure used to define $\epsilon$-pure differential privacy.

In the following proof definition, $d$ corresponds to $\epsilon$ when also quantified over all adjacent datasets. That is, $\epsilon$ is the greatest possible $d$ over all pairs of adjacent datasets $x, x’$ where $Y \sim M(x)$, $Y’ \sim M(x’)$. $M(\cdot)$ is a measurement (commonly known as a mechanism). The measurement’s input metric defines the notion of adjacency, and the measurement’s input domain defines the set of possible datasets.

Proof Definition

d-closeness

For any two distributions $Y, Y’$ and any non-negative $d$, $Y, Y’$ are $d$-close under the max divergence measure whenever

D_\infty(Y, Y') = \max_{S \subseteq \textrm{Supp}(Y)} \Big[\ln \dfrac{\Pr[Y \in S]}{\Pr[Y' \in S]} \Big] \leq d.

Trait Implementations

impl AmplifiableMeasure for MaxDivergence

fn amplify( &self, epsilon: &f64, population_size: usize, sample_size: usize, ) -> Fallible<f64>

impl ApproximateMeasure for MaxDivergence

fn add_delta(_d_out: Self::Distance, _delta_p: f64) -> Fallible<Self::Distance>

impl BasicCompositionMeasure for MaxDivergence

fn concurrent(&self) -> Fallible<bool>

fn compose(&self, d_i: Vec<Self::Distance>) -> Fallible<Self::Distance>

impl Clone for MaxDivergence

fn clone(&self) -> MaxDivergence

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MaxDivergence

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for MaxDivergence

fn default() -> MaxDivergence

Returns the “default value” for a type.

impl Measure for MaxDivergence

type Distance = f64

Proof Definition

impl NoiseExprMeasure for MaxDivergence

const DISTRIBUTION: Distribution = Distribution::Laplace

type Metric = LpDistance<1, f64>

fn map_function(scale: f64) -> impl Fn(&f64) -> Fallible<f64>

impl PartialEq for MaxDivergence

fn eq(&self, other: &MaxDivergence) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<MS> PrivateDslPlan<MS, MaxDivergence> for DslPlan

where MS: 'static + UnboundedMetric, DslPlan: StableDslPlan<MS, MS>,

fn make_private( self, input_domain: FrameDomain<DslPlan>, input_metric: MS, output_measure: MaxDivergence, global_scale: Option<f64>, threshold: Option<u32>, ) -> Fallible<Measurement<FrameDomain<DslPlan>, DslPlan, MS, MaxDivergence>>

impl<M: 'static + UnboundedMetric> PrivateExpr<PartitionDistance<M>, MaxDivergence> for Expr

fn make_private( self, input_domain: WildExprDomain, input_metric: PartitionDistance<M>, output_measure: MaxDivergence, global_scale: Option<f64>, ) -> Fallible<Measurement<WildExprDomain, ExprPlan, PartitionDistance<M>, MaxDivergence>>

impl StructuralPartialEq for MaxDivergence