def test_sample_without_replacement():
array = np.ones(100)
node_single = DataNode()
node_single.set_private_data(name="array", data=array)
sample_size = 50
def u(x, r):
output = np.zeros(len(r))
for i in range(len(r)):
output[i] = r[i] * sum(np.greater_equal(x, r[i]))
return output
r = np.arange(0, 3.5, 0.001)
delta_u = r.max()
epsilon = 5
exponential_mechanism = ExponentialMechanism(u,
r,
delta_u,
epsilon,
size=sample_size)
access_modes = [LaplaceMechanism(1, 1)]
access_modes.append(GaussianMechanism(1, (0.5, 0.5)))
access_modes.append(RandomizedResponseBinary(0.5, 0.5, 1))
access_modes.append(RandomizedResponseCoins())
access_modes.append(exponential_mechanism)
for a in access_modes:
sampling_method = SampleWithoutReplacement(a, sample_size, array.shape)
node_single.configure_data_access("array", sampling_method)
result = node_single.query("array")
assert result.shape[0] == sample_size
def test_randomize_binary_mechanism_no_binary():
array = np.random.rand(1000)
federated_array = shfl.private.federated_operation.federate_array(
array, 100)
federated_array.configure_data_access(
RandomizedResponseBinary(f0=0.5, f1=0.5, epsilon=1))
with pytest.raises(ValueError):
federated_array.query()
def test_randomize_binary_mechanism_no_binary_scalar():
scalar = 0.1
node_single = DataNode()
node_single.set_private_data(name="scalar", data=scalar)
data_access_definition = RandomizedResponseBinary(f0=0.5,
f1=0.5,
epsilon=1)
node_single.configure_data_access("scalar", data_access_definition)
with pytest.raises(ValueError):
node_single.query("scalar")
def test_randomize_binary_random_scalar_0():
scalar = 0
node_single = DataNode()
node_single.set_private_data(name="scalar", data=scalar)
data_access_definition = RandomizedResponseBinary(f0=0.5,
f1=0.5,
epsilon=1)
node_single.configure_data_access("scalar", data_access_definition)
result = node_single.query(private_property="scalar")
assert np.isscalar(result)
assert result == 0 or result == 1
def test_randomize_binary_mechanism_array_almost_always_false_values_zeros():
array = np.zeros(1000)
node_single = DataNode()
node_single.set_private_data(name="array", data=array)
# Prob of one given 1 very low, mean should be near 0
data_access_definition = RandomizedResponseBinary(f0=0.01,
f1=0.5,
epsilon=1)
node_single.configure_data_access("array", data_access_definition)
result = node_single.query("array")
assert np.abs(1 - np.mean(result)) < 0.05
def test_randomize_binary_mechanism_array_almost_always_true_values_ones():
array = np.ones(1000)
node_single = DataNode()
node_single.set_private_data(name="array", data=array)
# Prob of one given 1 very high, mean should be near 1
data_access_definition = RandomizedResponseBinary(f0=0.5,
f1=0.99,
epsilon=5)
node_single.configure_data_access("array", data_access_definition)
result = node_single.query("array")
assert 1 - np.mean(result) < 0.05
def test_randomize_binary_random():
data_size = 100
array = np.ones(data_size)
node_single = DataNode()
node_single.set_private_data(name="A", data=array)
data_access_definition = RandomizedResponseBinary(f0=0.5,
f1=0.5,
epsilon=1)
node_single.configure_data_access("A", data_access_definition)
result = node_single.query(private_property="A")
differences = 0
for i in range(data_size):
if result[i] != array[i]:
differences = differences + 1
assert 0 < differences < data_size
assert np.mean(result) < 1
def test_randomized_response_binary_epsilon_delta():
randomized_response_binary = RandomizedResponseBinary(f0=0.1,
f1=0.9,
epsilon=1)
assert randomized_response_binary.epsilon_delta is not None
def test_randomized_response_correctness():
with pytest.raises(ValueError):
RandomizedResponseBinary(0.1, 2, epsilon=20)
with pytest.raises(ValueError):
RandomizedResponseBinary(0.8, 0.8, epsilon=0.1)
def test_randomize_binary_deterministic():
array = np.array([0, 1])
node_single = DataNode()
node_single.set_private_data(name="A", data=array)
with pytest.raises(ValueError):
RandomizedResponseBinary(f0=1, f1=1, epsilon=1)