Class: Google::Cloud::Dlp::V2::PrivacyMetric

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/privacy/dlp/v2/dlp.rb

Overview

Privacy metric to compute for reidentification risk analysis.

Defined Under Namespace

Classes: CategoricalStatsConfig, DeltaPresenceEstimationConfig, KAnonymityConfig, KMapEstimationConfig, LDiversityConfig, NumericalStatsConfig

Instance Attribute Summary collapse

Instance Attribute Details

#categorical_stats_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::CategoricalStatsConfig

Returns Categorical stats.

Returns:



1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1567

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point
    #     number between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#delta_presence_estimation_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::DeltaPresenceEstimationConfig

Returns delta-presence.

Returns:



1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1567

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point
    #     number between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#k_anonymity_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::KAnonymityConfig

Returns K-anonymity.

Returns:



1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1567

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point
    #     number between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#k_map_estimation_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig

Returns k-map.

Returns:



1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1567

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point
    #     number between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#l_diversity_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::LDiversityConfig

Returns l-diversity.

Returns:



1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1567

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point
    #     number between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#numerical_stats_config ⇒ ::Google::Cloud::Dlp::V2::PrivacyMetric::NumericalStatsConfig

Returns Numerical stats.

Returns:



1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
 
# File 'proto_docs/google/privacy/dlp/v2/dlp.rb', line 1567

class PrivacyMetric
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Compute numerical stats over an individual column, including
  # min, max, and quantiles.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute numerical stats on. Supported types are
  #     integer, float, date, datetime, timestamp, time.
  class NumericalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Compute numerical stats over an individual column, including
  # number of distinct values and value count distribution.
  # @!attribute [rw] field
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Field to compute categorical stats on. All column types are
  #     supported except for arrays and structs. However, it may be more
  #     informative to use NumericalStats when the field type is supported,
  #     depending on the data.
  class CategoricalStatsConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # k-anonymity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of fields to compute k-anonymity over. When multiple fields are
  #     specified, they are considered a single composite key. Structs and
  #     repeated data types are not supported; however, nested fields are
  #     supported so long as they are not structs themselves or nested within
  #     a repeated field.
  # @!attribute [rw] entity_id
  #   @return [::Google::Cloud::Dlp::V2::EntityId]
  #     Message indicating that multiple rows might be associated to a
  #     single individual. If the same entity_id is associated to multiple
  #     quasi-identifier tuples over distinct rows, we consider the entire
  #     collection of tuples as the composite quasi-identifier. This collection
  #     is a multiset: the order in which the different tuples appear in the
  #     dataset is ignored, but their frequency is taken into account.
  #
  #     Important note: a maximum of 1000 rows can be associated to a single
  #     entity ID. If more rows are associated with the same entity ID, some
  #     might be ignored.
  class KAnonymityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # l-diversity metric, used for analysis of reidentification risk.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::FieldId>]
  #     Set of quasi-identifiers indicating how equivalence classes are
  #     defined for the l-diversity computation. When multiple fields are
  #     specified, they are considered a single composite key.
  # @!attribute [rw] sensitive_attribute
  #   @return [::Google::Cloud::Dlp::V2::FieldId]
  #     Sensitive field for computing the l-value.
  class LDiversityConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end

  # Reidentifiability metric. This corresponds to a risk model similar to what
  # is called "journalist risk" in the literature, except the attack dataset is
  # statistically modeled instead of being perfectly known. This can be done
  # using publicly available data (like the US Census), or using a custom
  # statistical model (indicated as one or several BigQuery tables), or by
  # extrapolating from the distribution of values in the input dataset.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::TaggedField>]
  #     Required. Fields considered to be quasi-identifiers. No two columns can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers column must appear in exactly one column
  #     of one auxiliary table.
  class KMapEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # A column with a semantic tag attached.
    # @!attribute [rw] field
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. Identifies the column.
    # @!attribute [rw] info_type
    #   @return [::Google::Cloud::Dlp::V2::InfoType]
    #     A column can be tagged with a InfoType to use the relevant public
    #     dataset as a statistical model of population, if available. We
    #     currently support US ZIP codes, region codes, ages and genders.
    #     To programmatically obtain the list of supported InfoTypes, use
    #     ListInfoTypes with the supported_by=RISK_ANALYSIS filter.
    # @!attribute [rw] custom_tag
    #   @return [::String]
    #     A column can be tagged with a custom tag. In this case, the user must
    #     indicate an auxiliary table that contains statistical information on
    #     the possible values of this column (below).
    # @!attribute [rw] inferred
    #   @return [::Google::Protobuf::Empty]
    #     If no semantic tag is indicated, we infer the statistical model from
    #     the distribution of values in the input data
    class TaggedField
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # An auxiliary table contains statistical information on the relative
    # frequency of different quasi-identifiers values. It has one or several
    # quasi-identifiers columns, and one column that indicates the relative
    # frequency of each quasi-identifier tuple.
    # If a tuple is present in the data but not in the auxiliary table, the
    # corresponding relative frequency is assumed to be zero (and thus, the
    # tuple is highly reidentifiable).
    # @!attribute [rw] table
    #   @return [::Google::Cloud::Dlp::V2::BigQueryTable]
    #     Required. Auxiliary table location.
    # @!attribute [rw] quasi_ids
    #   @return [::Array<::Google::Cloud::Dlp::V2::PrivacyMetric::KMapEstimationConfig::AuxiliaryTable::QuasiIdField>]
    #     Required. Quasi-identifier columns.
    # @!attribute [rw] relative_frequency
    #   @return [::Google::Cloud::Dlp::V2::FieldId]
    #     Required. The relative frequency column must contain a floating-point
    #     number between 0 and 1 (inclusive). Null values are assumed to be zero.
    class AuxiliaryTable
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # A quasi-identifier column has a custom_tag, used to know which column
      # in the data corresponds to which column in the statistical model.
      # @!attribute [rw] field
      #   @return [::Google::Cloud::Dlp::V2::FieldId]
      #     Identifies the column.
      # @!attribute [rw] custom_tag
      #   @return [::String]
      #     A auxiliary field.
      class QuasiIdField
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end

  # δ-presence metric, used to estimate how likely it is for an attacker to
  # figure out that one given individual appears in a de-identified dataset.
  # Similarly to the k-map metric, we cannot compute δ-presence exactly without
  # knowing the attack dataset, so we use a statistical model instead.
  # @!attribute [rw] quasi_ids
  #   @return [::Array<::Google::Cloud::Dlp::V2::QuasiId>]
  #     Required. Fields considered to be quasi-identifiers. No two fields can
  #     have the same tag.
  # @!attribute [rw] region_code
  #   @return [::String]
  #     ISO 3166-1 alpha-2 region code to use in the statistical modeling.
  #     Set if no column is tagged with a region-specific InfoType (like
  #     US_ZIP_5) or a region code.
  # @!attribute [rw] auxiliary_tables
  #   @return [::Array<::Google::Cloud::Dlp::V2::StatisticalTable>]
  #     Several auxiliary tables can be used in the analysis. Each custom_tag
  #     used to tag a quasi-identifiers field must appear in exactly one
  #     field of one auxiliary table.
  class DeltaPresenceEstimationConfig
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end