mortendahl

# compute and collect all model gradients as private inputs
model_grads = zip(*[
    tfe.define_private_input(
        data_owner.player_name,
        data_owner.compute_gradient)
    for data_owner in data_owners
])

# compute mean gradient securely
aggregated_model_grads = [

mortendahl

import tensorflow as tf
import tf_encrypted as tfe

class PredictionClient:

    @tfe.private_input
    def provide_input(self):
        """Load and preprocess input data."""

    @tfe.private_output

mortendahl

x_train_0, y_train_0 = tfe.define_private_input(
    data_owner_0.player_name,
    data_owner_0.provide_training_data)

x_train_1, y_train_1 = tfe.define_private_input(
    data_owner_1.player_name,
    data_owner_1.provide_training_data)

x_train = tfe.concat([x_train_0, x_train_1], axis=0)
y_train = tfe.concat([y_train_0, y_train_1], axis=0)

mortendahl

import tensorflow as tf

def provide_weights():""" Load from disk """
def provide_input(): """ Pre-process """
def receive_output(logits): return tf.print(tf.argmax(logits))

# get model weights
w0, b0, w1, b1, w2, b2 = provide_weights()

# get prediction input

mortendahl

import tensorflow as tf
import tf_encrypted as tfe

def provide_weights(): """Load model weight from disk using TensorFlow."""
def provide_input(): """Load and preprocess input data locally on the client."""
def receive_output(logits): return tf.print(tf.argmax(logits))

w0, b0, w1, b1, w2, b2 = provide_weights()

# run provide_input locally on the client and encrypt

mortendahl

Keybase proof

I hereby claim:

• I am mortendahl on github.
• I am mortendahl (https://keybase.io/mortendahl) on keybase.
• I have a public key ASAKQjQ6aPe_9DuRi8wdIfatfopYbMJVRcC2qsrjuXEQTgo

To claim this, I am signing this object: