def test_complex_nested_query(self):
with self.cached_session() as sess:
query_ab = gaussian_query.GaussianSumQuery(l2_norm_clip=1.0,
stddev=0.0)
query_c = gaussian_query.GaussianAverageQuery(l2_norm_clip=10.0,
sum_stddev=0.0,
denominator=2.0)
query_d = gaussian_query.GaussianSumQuery(l2_norm_clip=10.0,
stddev=0.0)
query = nested_query.NestedQuery(
[query_ab, {
'c': query_c,
'd': [query_d]
}])
record1 = [{
'a': 0.0,
'b': 2.71828
}, {
'c': (-4.0, 6.0),
'd': [-4.0]
}]
record2 = [{
'a': 3.14159,
'b': 0.0
}, {
'c': (6.0, -4.0),
'd': [5.0]
}]
query_result, _ = test_utils.run_query(query, [record1, record2])
result = sess.run(query_result)
expected = [{'a': 1.0, 'b': 1.0}, {'c': (1.0, 1.0), 'd': [1.0]}]
self.assertAllClose(result, expected)
def test_raises_with_non_sum(self):
class NonSumDPQuery(dp_query.DPQuery):
def initial_sample_state(self, template=None):
del template # Unused.
return None
def accumulate_preprocessed_record(self, sample_state,
preprocessed_record):
del sample_state, preprocessed_record # Unused.
return None
def merge_sample_states(self, sample_state_1, sample_state_2):
del sample_state_1, sample_state_2 # Unused.
return None
def get_noised_result(self, sample_state, global_state):
del sample_state, global_state # Unused.
return None
non_sum_query = NonSumDPQuery()
# This should work.
nested_query.NestedQuery(non_sum_query)
# This should not.
with self.assertRaises(TypeError):
nested_query.NestedSumQuery(non_sum_query)
def test_nested_query_with_noise(self):
with self.cached_session() as sess:
sum_stddev = 2.71828
denominator = 3.14159
query1 = gaussian_query.GaussianSumQuery(l2_norm_clip=1.5,
stddev=sum_stddev)
query2 = gaussian_query.GaussianAverageQuery(
l2_norm_clip=0.5,
sum_stddev=sum_stddev,
denominator=denominator)
query = nested_query.NestedQuery((query1, query2))
record1 = (3.0, [2.0, 1.5])
record2 = (0.0, [-1.0, -3.5])
query_result, _ = test_utils.run_query(query, [record1, record2])
noised_averages = []
for _ in range(1000):
noised_averages.append(tf.nest.flatten(sess.run(query_result)))
result_stddev = np.std(noised_averages, 0)
avg_stddev = sum_stddev / denominator
expected_stddev = [sum_stddev, avg_stddev, avg_stddev]
self.assertArrayNear(result_stddev, expected_stddev, 0.1)
def test_raises_with_non_sum(self):
class NonSumDPQuery(dp_query.DPQuery):
pass
non_sum_query = NonSumDPQuery()
# This should work.
nested_query.NestedQuery(non_sum_query)
# This should not.
with self.assertRaises(TypeError):
nested_query.NestedSumQuery(non_sum_query)
def test_nested_gaussian_sum_no_clip_no_noise(self):
with self.cached_session() as sess:
query1 = gaussian_query.GaussianSumQuery(l2_norm_clip=10.0,
stddev=0.0)
query2 = gaussian_query.GaussianSumQuery(l2_norm_clip=10.0,
stddev=0.0)
query = nested_query.NestedQuery([query1, query2])
record1 = [1.0, [2.0, 3.0]]
record2 = [4.0, [3.0, 2.0]]
query_result, _ = test_utils.run_query(query, [record1, record2])
result = sess.run(query_result)
expected = [5.0, [5.0, 5.0]]
self.assertAllClose(result, expected)
def test_nested_gaussian_average_with_clip_no_noise(self):
with self.cached_session() as sess:
query1 = gaussian_query.GaussianAverageQuery(
l2_norm_clip=4.0, sum_stddev=0.0, denominator=5.0)
query2 = gaussian_query.GaussianAverageQuery(
l2_norm_clip=5.0, sum_stddev=0.0, denominator=5.0)
query = nested_query.NestedQuery([query1, query2])
record1 = [1.0, [12.0, 9.0]] # Clipped to [1.0, [4.0, 3.0]]
record2 = [5.0, [1.0, 2.0]] # Clipped to [4.0, [1.0, 2.0]]
query_result, _ = test_utils.run_query(query, [record1, record2])
result = sess.run(query_result)
expected = [1.0, [1.0, 1.0]]
self.assertAllClose(result, expected)
def test_nested_query(self):
population_size = tf.Variable(0)
selection_probability = tf.Variable(1.0)
query1 = gaussian_query.GaussianAverageQuery(l2_norm_clip=4.0,
sum_stddev=2.0,
denominator=5.0)
query2 = gaussian_query.GaussianAverageQuery(l2_norm_clip=5.0,
sum_stddev=1.0,
denominator=5.0)
query = nested_query.NestedQuery([query1, query2])
query = privacy_ledger.QueryWithLedger(query, population_size,
selection_probability)
record1 = [1.0, [12.0, 9.0]]
record2 = [5.0, [1.0, 2.0]]
# First sample.
tf.compat.v1.assign(population_size, 10)
tf.compat.v1.assign(selection_probability, 0.1)
test_utils.run_query(query, [record1, record2])
expected_queries = [[4.0, 2.0], [5.0, 1.0]]
formatted = query.ledger.get_formatted_ledger_eager()
sample_1 = formatted[0]
self.assertAllClose(sample_1.population_size, 10.0)
self.assertAllClose(sample_1.selection_probability, 0.1)
self.assertAllClose(sorted(sample_1.queries), sorted(expected_queries))
# Second sample.
tf.compat.v1.assign(population_size, 20)
tf.compat.v1.assign(selection_probability, 0.2)
test_utils.run_query(query, [record1, record2])
formatted = query.ledger.get_formatted_ledger_eager()
sample_1, sample_2 = formatted
self.assertAllClose(sample_1.population_size, 10.0)
self.assertAllClose(sample_1.selection_probability, 0.1)
self.assertAllClose(sorted(sample_1.queries), sorted(expected_queries))
self.assertAllClose(sample_2.population_size, 20.0)
self.assertAllClose(sample_2.selection_probability, 0.2)
self.assertAllClose(sorted(sample_2.queries), sorted(expected_queries))
def test_record_incompatible_with_query(self, queries, record, error_type):
with self.assertRaises(error_type):
test_utils.run_query(nested_query.NestedQuery(queries), [record])
def __init__(
self,
l2_norm_clip,
noise_multiplier,
scalars,
num_microbatches=None,
ledger=None,
unroll_microbatches=False,
*args, # pylint: disable=keyword-arg-before-vararg
**kwargs):
query1 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[0], l2_norm_clip[0] * noise_multiplier[0],
scalars[0])
query2 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[1], l2_norm_clip[1] * noise_multiplier[1],
scalars[1])
query3 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[2], l2_norm_clip[2] * noise_multiplier[2],
scalars[2])
query4 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[3], l2_norm_clip[3] * noise_multiplier[3],
scalars[3])
query5 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[4], l2_norm_clip[4] * noise_multiplier[4],
scalars[4])
query6 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[5], l2_norm_clip[5] * noise_multiplier[5],
scalars[5])
query7 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[6], l2_norm_clip[6] * noise_multiplier[6],
scalars[6])
query8 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[7], l2_norm_clip[7] * noise_multiplier[7],
scalars[7])
query9 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[8], l2_norm_clip[8] * noise_multiplier[8],
scalars[8])
query10 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[9], l2_norm_clip[9] * noise_multiplier[9],
scalars[9])
query11 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[10], l2_norm_clip[10] * noise_multiplier[10],
scalars[10])
query12 = gaussian_query.GaussianAverageQuery(
l2_norm_clip[11], l2_norm_clip[11] * noise_multiplier[11],
scalars[11])
dp_nested_query = nested_query.NestedQuery([
query1, query2, query3, query4, query5, query6, query7, query8,
query9, query10, query11, query12
])
#dp_nested_query = nested_query.NestedQuery([query1, query2, query3])
if ledger:
dp_nested_query = privacy_ledger.QueryWithLedger(
dp_nested_query, ledger=ledger)
super(DPMultiGaussianOptimizerClass,
self).__init__(dp_nested_query, num_microbatches,
unroll_microbatches, *args, **kwargs)
