Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support for blackbox membership inference attack without true labels #2293

Merged

Conversation

abigailgold
Copy link
Collaborator

@abigailgold abigailgold commented Sep 20, 2023

Description

Support for blackbox membership inference attack without true labels. If not supplied, the attack is based only on model predictions.
This is not supported for 'loss' mode.

Fixes #2154

Type of change

Please check all relevant options.

  • Improvement (non-breaking)
  • Bug fix (non-breaking)
  • New feature (non-breaking)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Testing

Created new tests for the feature.

Test Configuration:

  • OS: MacOS 12.6.8
  • Python version: 3.9
  • ART version or commit number
  • TensorFlow / Keras / PyTorch / MXNet version

Checklist

  • My code follows the style guidelines of this project
  • I have performed a self-review of my own code
  • I have commented my code
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes
  • My changes have been tested using both CPU and GPU devices

Signed-off-by: abigailt <abigailt@il.ibm.com>
Signed-off-by: abigailt <abigailt@il.ibm.com>
Signed-off-by: abigailt <abigailt@il.ibm.com>
@codecov-commenter
Copy link

codecov-commenter commented Sep 20, 2023

Codecov Report

Merging #2293 (f4a4fa6) into dev_1.17.0 (cc03386) will increase coverage by 7.20%.
The diff coverage is 91.48%.

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

Impacted file tree graph

@@              Coverage Diff               @@
##           dev_1.17.0    #2293      +/-   ##
==============================================
+ Coverage       76.87%   84.08%   +7.20%     
==============================================
  Files             327      327              
  Lines           30777    30850      +73     
  Branches         5697     5716      +19     
==============================================
+ Hits            23660    25939    +2279     
+ Misses           5772     3450    -2322     
- Partials         1345     1461     +116     
Files Coverage Δ
...ttacks/inference/membership_inference/black_box.py 90.50% <91.48%> (+2.22%) ⬆️

... and 45 files with indirect coverage changes

@beat-buesser beat-buesser self-assigned this Sep 21, 2023
@beat-buesser beat-buesser added the enhancement New feature or request label Oct 10, 2023
@beat-buesser beat-buesser added this to the ART 1.17.0 milestone Oct 10, 2023
Copy link
Collaborator

@beat-buesser beat-buesser left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @abigailgold Thank you very much for your pull request adding support for black-box membership inference! It looks good to me. I'll fix the style check issues imported by me merging dev_1.17.0 in a separate commit.

@beat-buesser beat-buesser merged commit f4a4fa6 into Trusted-AI:dev_1.17.0 Dec 19, 2023
34 of 35 checks passed
@beat-buesser beat-buesser added this to Pull request done in ART 1.17.0 Dec 27, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
No open projects
ART 1.17.0
Pull request done
Development

Successfully merging this pull request may close these issues.

Support for blackbox membership inference attack without true labels
3 participants