Alle Klassen und Schnittstellen
Klasse
Beschreibung
This class implements an information loss which can be represented as a
decimal number per quasi-identifier.
This class implements an information loss which can be represented as a
decimal number per quasi-identifier.
This class provides an abstract skeleton for the implementation of multi-dimensional metrics.
This class provides an abstract skeleton for the implementation of metrics
that can either be precomputed or not.
This class provides an abstract skeleton for the implementation of single-dimensional metrics.
This abstract class represents an aggregate function.
A builder for aggregate functions.
An aggregate function that has a parameter.
An aggregate function that returns the arithmetic mean, if it may be computed, "NULL"
otherwise.
An aggregate function that returns the arithmetic mean of min Ungültige Eingabe: "&" max, if it may be computed, "NULL"
otherwise.
An aggregate function that returns an interval consisting of the
first and the last element following the predefined order .
An aggregate function that returns a common prefix.
An aggregate function that returns a constant value.
An aggregate function that returns the geometric mean, if it may be computed, "NULL"
otherwise.
An aggregate function that returns the geometric mean of min Ungültige Eingabe: "&" max, if it may be computed, "NULL"
otherwise.
An aggregate function that returns an interval [min, max] .
An aggregate function that returns a set of all data values.
An aggregate function that returns a set of the prefixes of the data values.
This class offers several methods to define parameters and execute the ARX
algorithm.
A PDF document
An base class for configuration classes for classification experiments
A generic configuration for the ARX anonymizer.
The algorithms supported by ARX
Class for internal use that provides access to more parameters and functionality.
Monotonicity.
The semantics of heuristic search steps.
Basic configuration of monetary amounts, such as the publisher's benefit
per record or the per-record fine fine for a successful re-identification attack.
Configuration for feature scaling
This class implements a representation of the generalization lattice that is
exposed to users of the API.
Reflects different anonymity properties.
Context for deserialization.
This class implements a listener for the ARX framework.
This class models population properties for risk estimation
Regions
Statistics about the anonymization process for output data
One individual anonymization step
Encapsulates the results of an execution of the ARX algorithm.
Runtime configuration for the solver
Represents an attribute type.
This class implements a generalization hierarchy.
The default implementation of a generalization hierarchy.
This class is used to define aggregate functions for microaggregation.
This class describes a microaggregation function
This criterion ensures that an estimate for the average re-identification risk falls
below a given threshold.
Basic-beta-Likeness:
Jianneng Cao, Panagiotis Karras:
Publishing Microdata with a Robust Privacy Guarantee
VLDB 2012.
Jianneng Cao, Panagiotis Karras:
Publishing Microdata with a Robust Privacy Guarantee
VLDB 2012.
This class represents cardinalities.
Style information for a PDF document
Enum for list styles
Configuration for logistic regression
Prior function for regularization
Configuration for naive bayes classification
Type of bayes classifier
Configuration for Random Forest classifiers
Split rule for the decision tree
A complete specification of all input and output data
Metadata about a single feature
Implements a classifier
A classification result
Internal class for interrupts.
Provides methods for creating checksums CSV encoded data.
This class implements a reader for CSV encoded information.
Provides methods for writing CSV encoded data.
Reads a CSV encoded generalization hierarchy.
Additional options for reading/writing CSV files
Syntax for a CSV file.
Represents input data for the ARX framework.
The default implementation of a data object.
Encapsulates a definition of the types of attributes contained in a dataset.
This class encapsulates a generalization scheme
A specific generalization degree
This class provides access to dictionary encoded data.
An implementation of the DataHandle interface for input data.
Wrapper class that provides information to StatisticsBuilder.
Interface
An implementation of the class DataHandle for output data.
This implementation of a data handle projects a given data handle onto a given research subset.
This class represents different scales of measure.
A selector for tuples.
This class provides configuration options for importing data from CSV-files, from Excel-files
or via a JDBC connection.
This class represents a the dataset that is to be de-identified
as a subset of the given population table.
This class provides access to the data types supported by the ARX framework.
Base class for date/time types.
Base class for numeric types.
Base class for numeric types.
Base class for ordered string types.
Base class for string types.
An entry in the list of available data types.
An interface for data types with format.
An interface for data types with a ratio scale.
Delta-disclosure privacy as proposed in:
Justin Brickell and Vitaly Shmatikov:
The Cost of Privacy: Destruction of Data-mining Utility in Anonymized Data Publishing
Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
2008
Justin Brickell and Vitaly Shmatikov:
The Cost of Privacy: Destruction of Data-mining Utility in Anonymized Data Publishing
Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
2008
The distinct l-diversity privacy criterion.
Base interface for domain shares.
This class represents a set of domain shares for an attribute.
This class represents a set of domain shares for an attribute.
This class represents a set of domain shares for an attribute.
This class represents a reliable set of domain shares for an attribute.
The d-presence criterion
Published in:
Nergiz M, Atzori M, Clifton C.
(e,d)-Differential Privacy implemented with SafePub as proposed in:
Bild R, Kuhn KA, Prasser F.
An abstract element
Complex element of data items
PDF list
PDF text element
PDF page break
PDF subtitle element
PDF text element
Style
PDF title element
PDF page break
Enhanced-beta-Likeness:
Jianneng Cao, Panagiotis Karras:
Publishing Microdata with a Robust Privacy Guarantee
VLDB 2012.
Jianneng Cao, Panagiotis Karras:
Publishing Microdata with a Robust Privacy Guarantee
VLDB 2012.
The entropy l-diversity privacy model.
Enumerator of entropy estimators for the entropy-l-diversity privacy model.
The t-closeness criterion with equal-distance EMD.
A privacy criterion that is explicitly bound to a sensitive attribute.
An implementation of the exponential mechanism for discrete domains as proposed in:
McSherry, Frank, and Kunal Talwar:
Mechanism design via differential privacy.
A very basic map using golden ratio hashing and linear probing.
A hash groupify operator.
Entry
The t-closeness criterion with hierarchical-distance EMD.
Base class for hierarchy builders.
The three types of builders.
This class enables building hierarchies for dates.
A format-class for localization
Granularity
This abstract base class enables building hierarchies for categorical and non-categorical values.
This class represents a fanout parameter.
This class represents a level in the hierarchy.
This class enables building hierarchies for non-categorical values by mapping them
into given intervals.
This class represents an interval.
For each direction, this class encapsulates three bounds.
This class enables building hierarchies for categorical and non-categorical values
by ordering the data items and merging into groups with predefined sizes.
A serializable comparator.
This class enables building hierarchies mostly for categorical variables
by iteratively removing the value with lowest priority
For priorities
This class enables building hierarchies for categorical and non-categorical values
using redaction.
Order
Utility class providing access to important constants for finding HIPAA identifiers.
Utility class providing access to important constants for finding HIPAA identifiers.
Provides information about the occurrence of an HIPPA identifier
Represents the HIPPA identifiers
Represents the classifier for the HIPAA identifier.
Interface to be implemented when columns can be referred to by an index.
This class implements an information loss which can be represented as a
decimal number per quasi-identifier.
This class implements an information loss which can be represented as a
decimal number per quasi-identifier.
This class implements an information loss which can be represented as a
decimal number per quasi-identifier.
This class implements an information loss which can be represented as a
decimal number per quasi-identifier.
This class implements an information loss which can be represented as a
decimal number per quasi-identifier.
Information loss with a potential lower bound.
This class implements information loss using score values for data-independent
differential privacy with appropriate comparison semantics
(i.e. higher score values are better).
This class implements an information loss which can be represented as a
single decimal number.
Information loss with a potential lower bound.
A privacy criterion that is implicitly bound to the quasi-identifiers.
Base adapter for all data sources
This defines properties and methods that all data source import adapters have
in common.
Import adapter for CSV files
This adapter can import data from a CSV file.
Import adapter for Excel files
This adapter can import data from Excel files.
Import adapter for JDBC
This adapter can import data from JDBC sources.
Represents a single data column
This represents a single column that will be imported from.
Represents a single CSV data column
CSV columns are referred to by an index (see
ImportColumnIndexed).Represents a single Excel data column
Excel columns are referred to by an index (see
ImportColumnIndexed).Superclass for column types that are only referred to by an index.
Represents a single JDBC data column
JDBC columns can be referred to by both an index (
) and
by name (
Ungültige Referenz
IIndexColumnIImportColumnNamed.Abstract base configuration
This abstract superclass defines properties that all configurations have
in common, i.e. a notion of columns, which can be added and retrieved.
Configuration describing a CSV file.
Configuration describing an Excel file
This is used to describe Excel files.
Valid file types for Excel files
XLS is the "old" Excel file type, XLSX is the "new" Excel file type.
Configuration describing a file in general
File based configurations should extend this class as the notion of a
ImportConfigurationFile.fileLocation is common to all of them.Configuration describing a JDBC source.
This is a special criterion that does not enforce any privacy guarantees
but allows to define a data subset.
This class implements an abstract base class for information loss.
Information loss with a potential lower bound.
Information loss with a potential lower bound.
Interval arithmetic system
Arithmetic exception
A basic double interval
This class implements serialization for maps
Utility for I/O
The k-anonymity criterion
Published in:
Sweeney L.
This class implements the k-map privacy model as proposed by Latanya Sweeney.
As an alternative to explicitly providing data about the underlying population, cell sizes can be can be estimated with the D3 (Poisson) and D4 (zero-truncated Poisson) estimators proposed in:
K.
As an alternative to explicitly providing data about the underlying population, cell sizes can be can be estimated with the D3 (Poisson) and D4 (zero-truncated Poisson) estimators proposed in:
K.
Estimators for cell sizes in the population.
An abstract base class for l-diversity criteria
Published in:
Machanavajjhala A, Kifer D, Gehrke J.
Abstract base class for metrics.
Pluggable aggregate functions.
This class provides an implementation of the (normalized) average equivalence class size metric.
A class for a configuration of a metric.
This class provides an abstract skeleton for the implementation of metrics.
A class describing a metric and its configuration options.
This class provides an implementation of the DM metric (non-monotonic).
This class provides an implementation of the DM* metric (monotonic variant of
the Discernability Metric).
This class provides an efficient implementation of the non-uniform entropy
metric.
This class provides an implementation of the Height metric.
This class provides an implementation of the Height metric.
This class implements a variant of the Loss metric.
This class implements a variant of the Loss metric.
This class implements a variant of the Loss metric.
This class provides an implementation of a weighted precision metric as
proposed in:
Sweeney, L. (2002).
Sweeney, L. (2002).
This class provides an implementation of the non-uniform entropy
metric.
This class provides an implementation of the non-uniform entropy
metric.
This class provides an efficient implementation of the non-uniform entropy
metric.
This class provides an implementation of the non-uniform entropy
metric.
This class provides an implementation of the non-uniform entropy
metric.
This class provides an implementation of the non-uniform entropy
metric.
This class provides an implementation of normalized non-uniform entropy.
This class provides an implementation of normalized non-uniform entropy.
This class provides an efficient implementation of normalized non-uniform entropy.
This class provides an implementation of a weighted precision metric as
proposed in:
Sweeney, L. (2002).
Sweeney, L. (2002).
This class provides an implementation of a static metric in
which information loss is user-defined per generalization level.
This class provides an efficient implementation of a non-monotonic and
non-uniform entropy metric.
This class provides an implementation of a weighted precision metric as
proposed in:
Sweeney, L. (2002).
Sweeney, L. (2002).
This class provides an implementation of a monotonic weighted precision metric.
This class provides an implementation of the (normalized) average equivalence class size metric.
This class provides an implementation of the classification metric.
This class provides an implementation of the monotonic DM* metric.
This class implements a variant of the Ambiguity metric.
This class provides an implementation of the non-monotonic DM metric.
This class implements a the entropy-based information loss model proposed in:
A Game Theoretic Framework for Analyzing Re-Identification Risk.
A Game Theoretic Framework for Analyzing Re-Identification Risk.
This class implements the KL Divergence metric.
This class implements a model which maximizes publisher benefit according to the model proposed in:
A Game Theoretic Framework for Analyzing Re-Identification Risk.
A Game Theoretic Framework for Analyzing Re-Identification Risk.
This class provides an implementation of a static metric in
which information loss is user-defined per generalization level.
This class provides an abstract skeleton for the implementation of weighted metrics.
Implements a classifier
A classification result
Implements a classifier
A classification result
Implements a classifier
A classification result
Implements a classifier
A classification result
The t-closeness criterion for ordered attributes.
Implements the parameter calculation for differential privacy as proposed in:
Bild R, Kuhn KA, Prasser F.
Class supporting parameter calculations and translations.
This criterion ensures that the population uniqueness falls below a given threshold.
An abstract base class for privacy criteria.
Privacy model for the game theoretic approach proposed in:
A Game Theoretic Framework for Analyzing Re-Identification Risk.
Privacy model for the "no-attack" variant of the game theoretic approach proposed in:
A Game Theoretic Framework for Analyzing Re-Identification Risk.
Privacy model for the game theoretic approach proposed in:
A Game Theoretic Framework for Analyzing Re-Identification Risk.
Privacy model for the "no-attack" variant of the game theoretic approach proposed in:
A Game Theoretic Framework for Analyzing Re-Identification Risk.
Aggregate function for multi-dimensional quality measures
Basic configuration for quality models
Parser for ranges
Base class for representing domain shares in this package
Raw domain-share (unencoded).
This class represents a set of domain shares for an attribute.
Base class for quality measures.
Quality measures for individual attributes.
A measure for the complete dataset.
A class encapsulating information about data quality
Implementation of the Loss measure, as proposed in:
Iyengar, V.: Transforming data to satisfy privacy constraints.
Iyengar, V.: Transforming data to satisfy privacy constraints.
Implementation of the Non-Uniform Entropy measure that can handle local recoding.
Implementation of the Precision measure, as proposed in:
L.
L.
Implementation of the mean squared error for individual columns
Implementation of the AECS measure, as proposed in:
K.
K.
Implementation of the Ambiguity measure, as described in:
Goldberger, Tassa: "Efficient Anonymizations with Enhanced Utility" Trans Data Priv
Goldberger, Tassa: "Efficient Anonymizations with Enhanced Utility" Trans Data Priv
Implementation of the Discernibility measure, as proposed in:
R.
R.
Implementation of the Sum of Squared Errors introduced in the supplementary material to:
D.
D.
SSE / SST as described in Solanas, Agusti, Antoni Martinez-Balleste, and J.
The recursive-(c,l)-diversity criterion.
This exception is raised if a privacy or risk model cannot be reliably implemented.
Abstract class for criteria that ensure that a certain risk measure is lower than or equal to a given threshold
A builder for risk estimates
A builder for risk estimates, interruptible
A class for analyzing attribute-related risks.
This class implements a cost/benefit analysis following the game-theoretic approach proposed in:
A Game Theoretic Framework for Analyzing Re-Identification Risk.
A Game Theoretic Framework for Analyzing Re-Identification Risk.
This class encapsulates information about equivalence classes in a data set
Class for risks based on population uniqueness.
The statistical model used for computing Dankar's estimate.
Class representing the distribution of risks in the sample
Class for analyzing re-identification risks of the current sample and mixed
risks which have been derived from privacy models
This class implements risk measures as proposed by El Emam in
"Guide to the De-Identification of Personal Health Information",
"Measuring the Probability of Re-Identification"
Journalist risk
Marketer risk
Prosecutor risk
A set of derived risk estimates
Class for risks based on sample uniqueness
This class implements risk measures as proposed by El Emam in
"Guide to the De-Identification of Personal Health Information",
"Measuring the Probability of Re-Identification" considering
suppressed values as a wildcard
This exception is raised if the method that was called has left output data in an
inconsistent state that may breach privacy.
A set of rows.
An abstract base class for sample-based privacy criteria.
This criterion ensures that the sample uniqueness falls below a given threshold.
A class offering basic descriptive statistics about data handles.
A class offering basic descriptive statistics about data handles.
Statistics representing the performance of various classifiers
A ROC curve
A contingency table.
An entry in the contingency table.
Statistics about the equivalence classes.
A frequency distribution.
Encapsulates statistics obtained using various quality models
A base class for summary statistics
An abstract base class for t-closeness criteria as proposed in:
Li N, Li T, Venkatasubramanian S.
A class that supports associating input with output
For hash tables
Internal class for unexpected errors.
Class for accessing the water mark
Helper class
Helper class
This internal class provides access to version 2 of all metrics.