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_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(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_nested_query(self):
population_size = tf.Variable(0)
selection_probability = tf.Variable(0.0)
ledger = privacy_ledger.PrivacyLedger(population_size,
selection_probability, 50, 50)
query1 = gaussian_query.GaussianAverageQuery(l2_norm_clip=4.0,
sum_stddev=2.0,
denominator=5.0,
ledger=ledger)
query2 = gaussian_query.GaussianAverageQuery(l2_norm_clip=5.0,
sum_stddev=1.0,
denominator=5.0,
ledger=ledger)
query = nested_query.NestedQuery([query1, query2])
query = privacy_ledger.QueryWithLedger(query, ledger)
record1 = [1.0, [12.0, 9.0]]
record2 = [5.0, [1.0, 2.0]]
# First sample.
tf.assign(population_size, 10)
tf.assign(selection_probability, 0.1)
test_utils.run_query(query, [record1, record2])
expected_queries = [[4.0, 2.0], [5.0, 1.0]]
formatted = 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.assign(population_size, 20)
tf.assign(selection_probability, 0.2)
test_utils.run_query(query, [record1, record2])
formatted = 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_no_privacy_average(self):
with self.cached_session() as sess:
record1 = tf.constant([5.0, 0.0])
record2 = tf.constant([-1.0, 2.0])
query = no_privacy_query.NoPrivacyAverageQuery()
query_result = test_utils.run_query(query, [record1, record2])
result = sess.run(query_result)
expected = [2.0, 1.0]
self.assertAllClose(result, expected)
def test_gaussian_sum_no_clip_no_noise(self):
with self.cached_session() as sess:
record1 = tf.constant([2.0, 0.0])
record2 = tf.constant([-1.0, 1.0])
query = gaussian_query.GaussianSumQuery(
l2_norm_clip=10.0, stddev=0.0)
query_result, _ = test_utils.run_query(query, [record1, record2])
result = sess.run(query_result)
expected = [1.0, 1.0]
self.assertAllClose(result, expected)
def test_gaussian_sum_with_clip_no_noise(self):
with self.cached_session() as sess:
record1 = tf.constant([-6.0, 8.0]) # Clipped to [-3.0, 4.0].
record2 = tf.constant([4.0, -3.0]) # Not clipped.
query = gaussian_query.GaussianSumQuery(
l2_norm_clip=5.0, stddev=0.0)
query_result, _ = test_utils.run_query(query, [record1, record2])
result = sess.run(query_result)
expected = [1.0, 1.0]
self.assertAllClose(result, expected)
def test_gaussian_average_no_noise(self):
with self.cached_session() as sess:
record1 = tf.constant([5.0, 0.0]) # Clipped to [3.0, 0.0].
record2 = tf.constant([-1.0, 2.0]) # Not clipped.
query = gaussian_query.GaussianAverageQuery(
l2_norm_clip=3.0, sum_stddev=0.0, denominator=2.0)
query_result, _ = test_utils.run_query(query, [record1, record2])
result = sess.run(query_result)
expected_average = [1.0, 1.0]
self.assertAllClose(result, expected_average)
def test_sum_query(self):
record1 = tf.constant([2.0, 0.0])
record2 = tf.constant([-1.0, 1.0])
population_size = tf.Variable(0)
selection_probability = tf.Variable(0.0)
ledger = privacy_ledger.PrivacyLedger(population_size,
selection_probability, 50, 50)
query = gaussian_query.GaussianSumQuery(l2_norm_clip=10.0,
stddev=0.0,
ledger=ledger)
query = privacy_ledger.QueryWithLedger(query, ledger)
# First sample.
tf.assign(population_size, 10)
tf.assign(selection_probability, 0.1)
test_utils.run_query(query, [record1, record2])
expected_queries = [[10.0, 0.0]]
formatted = 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(sample_1.queries, expected_queries)
# Second sample.
tf.assign(population_size, 20)
tf.assign(selection_probability, 0.2)
test_utils.run_query(query, [record1, record2])
formatted = 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(sample_1.queries, expected_queries)
self.assertAllClose(sample_2.population_size, 20.0)
self.assertAllClose(sample_2.selection_probability, 0.2)
self.assertAllClose(sample_2.queries, expected_queries)
def test_no_privacy_weighted_average(self):
with self.cached_session() as sess:
record1 = tf.constant([4.0, 0.0])
record2 = tf.constant([-1.0, 1.0])
weights = [1, 3]
query = no_privacy_query.NoPrivacyAverageQuery()
query_result, _ = test_utils.run_query(query, [record1, record2],
weights=weights)
result = sess.run(query_result)
expected = [0.25, 0.75]
self.assertAllClose(result, expected)
def test_no_privacy_weighted_sum(self):
with self.cached_session() as sess:
record1 = tf.constant([2.0, 0.0])
record2 = tf.constant([-1.0, 1.0])
weight1 = 1
weight2 = 2
query = no_privacy_query.NoPrivacySumQuery()
query_result = test_utils.run_query(query, [record1, record2],
[weight1, weight2])
result = sess.run(query_result)
expected = [0.0, 2.0]
self.assertAllClose(result, expected)
def test_gaussian_sum_with_noise(self):
with self.cached_session() as sess:
record1, record2 = 2.71828, 3.14159
stddev = 1.0
query = gaussian_query.GaussianSumQuery(
l2_norm_clip=5.0, stddev=stddev)
query_result, _ = test_utils.run_query(query, [record1, record2])
noised_sums = []
for _ in xrange(1000):
noised_sums.append(sess.run(query_result))
result_stddev = np.std(noised_sums)
self.assertNear(result_stddev, stddev, 0.1)
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_gaussian_average_with_noise(self):
with self.cached_session() as sess:
record1, record2 = 2.71828, 3.14159
sum_stddev = 1.0
denominator = 2.0
query = gaussian_query.GaussianAverageQuery(
l2_norm_clip=5.0, sum_stddev=sum_stddev, denominator=denominator)
query_result, _ = test_utils.run_query(query, [record1, record2])
noised_averages = []
for _ in range(1000):
noised_averages.append(sess.run(query_result))
result_stddev = np.std(noised_averages)
avg_stddev = sum_stddev / denominator
self.assertNear(result_stddev, avg_stddev, 0.1)
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_gaussian_sum_with_changing_clip_no_noise(self):
with self.cached_session() as sess:
record1 = tf.constant([-6.0, 8.0]) # Clipped to [-3.0, 4.0].
record2 = tf.constant([4.0, -3.0]) # Not clipped.
l2_norm_clip = tf.Variable(5.0)
l2_norm_clip_placeholder = tf.placeholder(tf.float32)
assign_l2_norm_clip = tf.assign(l2_norm_clip, l2_norm_clip_placeholder)
query = gaussian_query.GaussianSumQuery(
l2_norm_clip=l2_norm_clip, stddev=0.0)
query_result, _ = test_utils.run_query(query, [record1, record2])
self.evaluate(tf.global_variables_initializer())
result = sess.run(query_result)
expected = [1.0, 1.0]
self.assertAllClose(result, expected)
sess.run(assign_l2_norm_clip, {l2_norm_clip_placeholder: 0.0})
result = sess.run(query_result)
expected = [0.0, 0.0]
self.assertAllClose(result, expected)
def test_incompatible_records(self, record1, record2, error_type):
query = no_privacy_query.NoPrivacySumQuery()
with self.assertRaises(error_type):
test_utils.run_query(query, [record1, record2])
def test_incompatible_records(self, record1, record2, error_type):
query = gaussian_query.GaussianSumQuery(1.0, 0.0)
with self.assertRaises(error_type):
test_utils.run_query(query, [record1, record2])
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])
