Review tabular example#402
Closed
fazelehh wants to merge 6 commits into
Closed
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
fazelehh
force-pushed
the
review_tabular_example
branch
from
a496c7c to
a7ba96a
Compare
Collaborator
Author
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR adds tabular model inversion (MINV) examples and extends the PLGMI attack to support tabular data modalities.
New examples
examples/minv/celebA_attributes/— MINV example on CelebA tabular attributes, supporting both PyTorch (ResNet) and XGBoost target modelsexamples/minv/mimic/— MINV example on MIMIC-III clinical data using CTGAN-based generator and PyTorch Tabular target modelCore changes
leakpro/attacks/minv_attacks/plgmi.py— Extended PLGMI to support tabular data: new differentiable tabular optimization path (optimize_z_grad), per-sample multi-restart optimization (optimize_z_grad_per_sample), and reference model support (load_reference_model,compute_total_loss)leakpro/input_handler/modality_extensions/tabular_metrics.py— New tabular-specific metrics for evaluating MINV attacksleakpro/attacks/utils/gan_handler.py/generator_handler.py— Extended GAN handler to support tabular CTGAN generatorsleakpro/input_handler/minv_handler.py— Extended MINV handler for tabular data formatleakpro/attacks/minv_attacks/abstract_minv.py/leakpro/schemas.py/leakpro/input_handler/user_imports.py— Schema and import updates to support new modalityData privacy
.gitignore.