org.deidentifier.arx.criteria

Class AverageReidentificationRisk

java.lang.Object

org.deidentifier.arx.criteria.PrivacyCriterion

org.deidentifier.arx.criteria.SampleBasedCriterion

org.deidentifier.arx.criteria.RiskBasedCriterion

org.deidentifier.arx.criteria.AverageReidentificationRisk

All Implemented Interfaces:

java.io.Serializable

public class AverageReidentificationRisk
extends RiskBasedCriterion

This criterion ensures that an estimate for the average re-identification risk falls below a given threshold. Furthermore a relaxed variant of this model is also implemented, supporting average risk, highest risk and a fraction of records allowed to exceed the highest risk

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
AverageReidentificationRisk(double riskThreshold) Creates a new instance of this model.
AverageReidentificationRisk(double averageRisk, double highestRisk, double recordsAtRisk) Creates a new instance of a relaxed variant of this model with average risk, highest risk and the fraction of records with a risk exceeding the highest risk.

Method Summary

Modifier and Type	Method and Description
AverageReidentificationRisk	clone() Clone
double	getAverageRisk()
double	getEffectiveHighestRisk() Returns the effective highest risk, i.e. the threshold that is actually being used by the software.
double	getHighestRisk() Returns the threshold set by the user.
double	getRecordsAtRisk()
double	getRiskThresholdMarketer() Return marketer risk threshold, 1 if there is none
boolean	isLocalRecodingSupported() Returns whether the criterion supports local recoding.
ElementData	render() Renders the privacy model
java.lang.String	toString() Returns a string representation.

Methods inherited from class org.deidentifier.arx.criteria.RiskBasedCriterion

enforce, getRequirements, getRiskThreshold

Methods inherited from class org.deidentifier.arx.criteria.SampleBasedCriterion

isAnonymous, isSampleBased

Methods inherited from class org.deidentifier.arx.criteria.PrivacyCriterion

clone, getDataSubset, getMinimalClassSize, getPopulationModel, getRiskThresholdJournalist, getRiskThresholdProsecutor, getSubset, initialize, isHeuristicSearchSupported, isHeuristicSearchWithTimeLimitSupported, isMinimalClassSizeAvailable, isMonotonicWithGeneralization, isMonotonicWithSuppression, isOptimalSearchSupported, isSubsetAvailable

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

AverageReidentificationRisk

public AverageReidentificationRisk(double riskThreshold)

Creates a new instance of this model.

Parameters:

riskThreshold -

AverageReidentificationRisk

public AverageReidentificationRisk(double averageRisk,
                                   double highestRisk,
                                   double recordsAtRisk)

Creates a new instance of a relaxed variant of this model with average risk, highest risk and the fraction of records with a risk exceeding the highest risk. Note: Due to rounding issues, the highest risk may be exceeded by up to 1%. To see the threshold that is actually being used, invoke getEffectiveHighestRisk()

Parameters:

averageRisk -

highestRisk -

recordsAtRisk -

Method Detail

clone

public AverageReidentificationRisk clone()

Description copied from class: PrivacyCriterion

Clone

Specified by:

clone in class PrivacyCriterion

getAverageRisk

public double getAverageRisk()

Returns:

the average risk

getEffectiveHighestRisk

public double getEffectiveHighestRisk()

Returns the effective highest risk, i.e. the threshold that is actually being used by the software.

Returns:

the highest risk

getHighestRisk

public double getHighestRisk()

Returns the threshold set by the user. Please consider the effective threshold, i.e. the threshold that is actually being used by the software.

Returns:

the highest risk

getRecordsAtRisk

public double getRecordsAtRisk()

Returns:

the records at risk

getRiskThresholdMarketer

public double getRiskThresholdMarketer()

Return marketer risk threshold, 1 if there is none

Overrides:

getRiskThresholdMarketer in class PrivacyCriterion

Returns:

isLocalRecodingSupported

public boolean isLocalRecodingSupported()

Description copied from class: PrivacyCriterion

Returns whether the criterion supports local recoding.

Specified by:

isLocalRecodingSupported in class PrivacyCriterion

Returns:

render

public ElementData render()

Description copied from class: PrivacyCriterion

Renders the privacy model

Specified by:

render in class PrivacyCriterion

Returns:

toString

public java.lang.String toString()

Description copied from class: PrivacyCriterion

Returns a string representation.

Specified by:

toString in class PrivacyCriterion