forked from 626_privacy/tensorflow_privacy
Add comment to explain support for LR
This commit is contained in:
parent
bfc5ef333a
commit
641c4dd98c
1 changed files with 4 additions and 0 deletions
|
@ -188,6 +188,10 @@ def run_seq2seq_attack(attack_input: Seq2SeqAttackInputData,
|
||||||
the attack result.
|
the attack result.
|
||||||
"""
|
"""
|
||||||
attack_input.validate()
|
attack_input.validate()
|
||||||
|
|
||||||
|
# The attacker uses the average rank (a single number) of a seq2seq dataset
|
||||||
|
# record to determine membership. Hence, only Logistic Regression is supported,
|
||||||
|
# as it makes the most sense for single-number features.
|
||||||
attacker = models.LogisticRegressionAttacker()
|
attacker = models.LogisticRegressionAttacker()
|
||||||
|
|
||||||
prepared_attacker_data = models.create_seq2seq_attacker_data(
|
prepared_attacker_data = models.create_seq2seq_attacker_data(
|
||||||
|
|
Loading…
Reference in a new issue