ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more

Module: tf_privacy

TensorFlow Privacy library.


restart_query module: Implements DPQuery interface for restarting the states of another query.

tree_aggregation module: Tree aggregation algorithm.

v1 module: TensorFlow Privacy library v1 imports.


class ComposedDpEvent: A series of composed mechanisms.

class DNNClassifier: DP version of tf.estimator.DNNClassifier.

class DPKerasAdagradOptimizer: Differentially private subclass of class tf.keras.optimizers.Adagrad.

class DPKerasAdamOptimizer: Differentially private subclass of class tf.keras.optimizers.Adam.

class DPKerasSGDOptimizer: Differentially private subclass of class tf.keras.optimizers.SGD.

class DPModel: DP subclass of tf.keras.Model.

class DPQuery: Interface for differentially private query mechanisms.

class DPSequential: DP subclass of tf.keras.Sequential.

class DiscreteGaussianSumQuery: Implements DPQuery for discrete Gaussian sum queries.

class DistributedDiscreteGaussianSumQuery: Implements DPQuery for discrete distributed Gaussian sum queries.

class DpEvent: Base class for DpEvents.

class FixedBatchSampledWorDpEvent: Sampling exactly batch_size records without replacement.

class FixedBatchSampledWrDpEvent: Sampling exactly batch_size records with replacement.

class GaussianDpEvent: The Gaussian mechanism.

class GaussianSumQuery: Implements DPQuery interface for Gaussian sum queries.

class NestedQuery: Implements DPQuery interface for structured queries.

class NoOpDpEvent: A DpEvent to represent operations with no privacy impact.

class NoPrivacyAverageQuery: Implements DPQuery interface for an average query with no privacy.

class NoPrivacyQuantileEstimatorQuery: Iterative process to estimate target quantile of a univariate distribution.

class NoPrivacySumQuery: Implements DPQuery interface for a sum query with no privacy.

class NonPrivateDpEvent: A DpEvent to represent non-private operations.

class NormalizedQuery: DPQuery for queries with a DPQuery numerator and fixed denominator.

class PoissonSampledDpEvent: An application of Poisson subsampling.

class QuantileAdaptiveClipSumQuery: DPQuery for Gaussian sum queries with adaptive clipping.

class QuantileEstimatorQuery: DPQuery to estimate target quantile of a univariate distribution.

class RestartQuery: DPQuery for SumAggregationDPQuery with a reset_state function.

class SelfComposedDpEvent: A mechanism composed with itself multiple times.

class ShuffledDatasetDpEvent: Shuffling a dataset and applying a mechanism to each partition.

class SumAggregationDPQuery: Base class for DPQueries that aggregate via sum.

class TreeAggregationDpEvent: Applying a series of mechanisms with tree aggregation.

class TreeCumulativeSumQuery: Returns private cumulative sums by clipping and adding correlated noise.

class TreeRangeSumQuery: Implements dp_query for accurate range queries using tree aggregation.

class TreeResidualSumQuery: Implements DPQuery for adding correlated noise through tree structure.

class UnsupportedDpEvent: A DpEvent to represent as-yet unsupported operations.

class VectorizedDPKerasAdagradOptimizer: Vectorized differentially private subclass of given class

class VectorizedDPKerasAdamOptimizer: Vectorized differentially private subclass of given class

class VectorizedDPKerasSGDOptimizer: Vectorized differentially private subclass of given class


compute_dp_sgd_privacy(...): Compute epsilon based on the given hyperparameters.

compute_heterogeneous_rdp(...): Computes RDP of Heteregoneous Applications of Sampled Gaussian Mechanisms.

compute_rdp(...): Computes RDP of the Sampled Gaussian Mechanism.

get_privacy_spent(...): Computes delta (or eps) for given eps (or delta) from RDP values.

make_dp_model_class(...): Given a subclass of tf.keras.Model, returns a DP-SGD version of it.

make_keras_optimizer_class(...): Given a subclass of tf.keras.optimizers.Optimizer, returns a DP-SGD subclass of it.

make_vectorized_keras_optimizer_class(...): Given a subclass of tf.keras.optimizers.Optimizer, returns a vectorized DP-SGD subclass of it.

version '0.7.3'