Add threshold-entropy attack #131
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CdavM
suggested changes
Oct 23, 2020
|
|
||
| @property | ||
| def is_trained_attack(self): | ||
| """Returns whether this type of attack requires training a model.""" | ||
| return self != AttackType.THRESHOLD_ATTACK | ||
| return (self != AttackType.THRESHOLD_ATTACK) & (self != AttackType.THRESHOLD_ENTROPY_ATTACK) |
There was a problem hiding this comment.
Can we use words instead, i.e. self != AttackType.THRESHOLD_ATTACK and self != AttackType.THRESHOLD_ENTROPY_ATTACK
| @@ -96,6 +96,19 @@ def _run_threshold_attack(attack_input: AttackInputData): | |||
| attack_type=AttackType.THRESHOLD_ATTACK, | |||
| roc_curve=roc_curve) | |||
|
|
|||
| def _run_threshold_entropy_attack(attack_input: AttackInputData): | |||
There was a problem hiding this comment.
Can we add an end-to-end test for this to membership_inference_attack_test.py? Something like the "test_run_attack_threshold_calculates_correct_auc" test
There was a problem hiding this comment.
The test case is added!
I have fixed these issues, please take another look, thanks. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Following our recent paper https://arxiv.org/pdf/2003.10595.pdf, I implement the code to run membership inference attacks by setting a threshold value on the prediction entropy value.
Compared to THRESHOLD_ATTACK, THRESHOLD_ENTROPY_ATTACK leverages the entropy value instead of the loss value.