tf_privacy.DPModel

Stay organized with collections Save and categorize content based on your preferences.

DP subclass of tf.keras.Model.

tf_privacy.DPModel(
    l2_norm_clip,
    noise_multiplier,
    num_microbatches=None,
    use_xla=True,
    *args,
    **kwargs
)

This can be used as a differentially private replacement for tf.keras.Model. This class implements DP-SGD using the standard Gaussian mechanism.

When instantiating this class, you need to supply several DP-related arguments followed by the standard arguments for Model.

Examples:

# Create Model instance.
model = DPModel(l2_norm_clip=1.0, noise_multiplier=0.5, use_xla=True,
         <standard arguments>)

You should use your DPModel instance with a standard instance of tf.keras.Optimizer as the optimizer, and a standard reduced loss. You do not need to use a differentially private optimizer.

# Use a standard (non-DP) optimizer.
optimizer = tf.keras.optimizers.SGD(learning_rate=0.01)

# Use a standard reduced loss.
loss = tf.keras.losses.MeanSquaredError()

model.compile(optimizer=optimizer, loss=loss)
model.fit(train_data, train_labels, epochs=1, batch_size=32)

l2_norm_clip Clipping norm (max L2 norm of per microbatch gradients).
noise_multiplier Ratio of the standard deviation to the clipping norm.
num_microbatches Number of microbatches.
use_xla If True, compiles train_step to XLA.
*args These will be passed on to the base class __init__ method.
**kwargs These will be passed on to the base class __init__ method.