apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-04-24 20:36:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
142 commits 9 branches 4 tags 2.3 MiB
Commit graph

142 commits

This branch
This branch
All branches
Author SHA1 Message Date
abigailgold
26addd192f
Support pytorch models in data minimization (#85) 
* Support pytorch models in data minimization

Signed-off-by: abigailt <abigailt@il.ibm.com>
 2023-09-21 17:48:15 +03:00
andersonm-ibm
a40484e0c9
Add column distribution comparison, and a third method for dataset asssessment by membership classification (#84) 
* Add column distribution comparison, and a third method for dataset assessment by membership classification

* Address review comments, add additional distribution comparison tests and make them externally configurable too, in addition to the alpha becoming configurable.

Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-09-21 16:43:19 +03:00
abigailgold
13a0567183
Make data minimization more consistent and performant (#83) 
* Update requirements

* Update incompatible scipy version

* Reduce runtime of dataset assessment tests

* ncp is now a class that contains 3 values: fit_score, transform_score and generalizations_score so that it doesn't matter in what order the different methods are called, all calculated ncp scores are stored.
Generalizations can now be applied either from tree cells or from global generalizations struct depending on the value of generalize_using_transform. Representative values can also be computed from global generalizations.
Removing a feature from the generalization can also be applied in either mode.

* Compute generalizations with test data when possible (for computing better representatives).

* Externalize common test code to methods.
 2023-08-21 18:39:15 +03:00
andersonm-ibm
e9a225501f
Limit scikit-learn version because of API changes (#81) 
* Limit scikit-learn versions between 0.22.2 and 1.1.3, remove deprecated load_boston().

* Set pytest configuration option to show test progress in detail.

* Change np.int to int according to DeprecationWarning

Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-05-14 08:52:06 +03:00
abigailgold
be7d248c33
Update README.md (#78) 
Add openssf badge.

Signed-off-by: Abigail Goldsteen <abigailt@il.ibm.com>
 2023-05-11 12:30:13 +03:00
andersonm-ibm
3885ab9d9d
Change back flake8 warnings to errors. Fix tests not to fail it. (#76) 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-05-11 11:33:50 +03:00
abigailgold
f2f8ddc877
Fix rtd docs (#75) 
* Fix issue building docs with new urllib3
* Try to fix rtd build

Signed-off-by: abigailt <abigailt@il.ibm.com>
 2023-05-09 13:30:28 +03:00
abigailgold
8a9ef80146
Increase version to 0.2.0 (#74) 
* Remove tensorflow dependency if not using keras model
* Remove xgboost dependency if not using xgboost model
* Documentation updates

Signed-off-by: abigailt <abigailt@il.ibm.com>
 2023-05-08 12:50:55 +03:00
andersonm-ibm
782edabd58
Add dataset privacy risk assessment example notebook. (#73) 
* Add dataset assessment notebook and reference to module from project README

Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-05-04 12:21:42 +03:00
Maya Anderson
dbb958f791 Merge pull request #71 from IBM/dataset_assessment 
Add AI privacy Dataset assessment module with two attack implementations.

Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-20 14:21:29 +02:00
abigailgold
c153635e4d
Welcome contributions in readme (#69) 
Signed-off-by: abigailt <abigailt@il.ibm.com>
 2023-01-11 19:10:43 +02:00
abigailgold
d52fcd0041
Formatting (#68) 
Fix most flake/lint errors and ignore a few others

Signed-off-by: abigailt <abigailt@il.ibm.com>
 2022-12-25 15:13:57 +02:00
andersonm-ibm
b47ba24906 Create CI test workflow using GitHub Actions 
Run Lint and PyTest on Python 3.8

Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2022-12-21 11:42:08 +02:00
abigailt
a76c3d2714 Fix random state to make tests pass 
Signed-off-by: abigailt <abigailt@il.ibm.com>
 2022-12-21 09:51:49 +02:00
abigailt
ba88bc09ba Add option for non-stratified split in minimizer 
Signed-off-by: abigailt <abigailt@il.ibm.com>
 2022-12-21 09:23:19 +02:00
Maya Anderson
89bdcfc00e Prepare project for CI: cleanup dependencies, fix test data location, cleanup assert. 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2022-12-20 16:00:36 +02:00
abigailt
805a489201 Add method to get predict function from blackbox classifier, add loss and optimizer params for pytorch models to generate shadow models 
Signed-off-by: abigailt <abigailt@il.ibm.com>
 2022-11-09 14:42:55 +02:00
abigailt
44d012857f Add loss and optimizer as properties 
Signed-off-by: abigailt <abigailt@il.ibm.com>
 2022-10-19 17:29:40 +03:00
abigailgold
1385f31dcf
Merge pull request #58 from IBM/pytorch_wrapper 
Wrapper for Pytorch models
 2022-08-02 17:23:46 +03:00
abigailt
64038f76f9 Merge with main 2022-08-01 18:12:03 +03:00
abigailt
dc5cc793ee Merge with main 2022-08-01 18:11:34 +03:00
abigailt
a9e2a35e18 Add support for xgboost XGBClassifier (#53) 2022-07-28 17:21:24 +03:00
olasaadi
74ce92acc4 fix 2022-07-26 18:37:44 +03:00
abigailt
a13415ad67 Externalize BlackboxClassifier dataset (x and predictions) 2022-07-25 16:31:45 +03:00
abigailt
fb534f7a0f BlackboxClassifier based on predictions to work with DatasetWithPredictions 2022-07-25 16:31:45 +03:00
abigailt
77a6e08c8e Keras regression support 2022-07-24 18:45:50 +03:00
Ron Shmelkin
521a2ccda9
add art to requirements.txt 2022-07-24 15:34:04 +03:00
Ron Shmelkin
15d7008224
remove self from array2numpy and array2torch_tensor functions 2022-07-24 15:32:09 +03:00
Ron Shmelkin
c77e34e373
update pytorch wrapper to use torch loaders 
fix tests
and dataset style
 2022-07-24 14:31:47 +03:00
olasaadi
fdc6005fce add validation set 2022-07-22 01:01:45 +03:00
olasaadi
65388da605 fix docstring 2022-07-20 18:39:53 +03:00
olasaadi
c2c7a01078 fix bug 2022-07-20 18:36:58 +03:00
olasaadi
6f69f5557b fix bug 2022-07-20 18:29:48 +03:00
olasaadi
3bf26b67d2 fix 2022-07-20 17:36:00 +03:00
abigailt
a7d156660e Wrap predict method in BlackBoxClassifierPredictMethod to avoid exception in ART when supplied method returns scalars 2022-07-20 13:33:19 +03:00
abigailt
1cc73b3da1 Check for mismatch between model output type and actual output 2022-07-20 13:33:19 +03:00
abigailt
bc7ab0cc7f Add model type to blackbox classifier (#49) 2022-07-20 13:33:19 +03:00
olasaadi
4973fbebc6 fix 2022-07-19 21:16:39 +03:00
abigailt
bc28f7f26a Return None where no predictions are available 2022-07-12 09:47:32 +03:00
abigailgold
00f9c16863
Support additional use cases for data (#46) 
* Make ART black box classifier not apply preprocessing to data
* Add option to store predictions (in addition to x,y) in Dataset and Data classes
 2022-07-11 14:28:09 +03:00
Shlomit Shachor
e25e58b253
enhance calculation of nb classes + tests (#45) 
* update get_nb_classes method to handle 1-hot and scalar input
 2022-07-05 11:32:17 +03:00
olasaadi
07e64b1f86 fix 2022-07-04 12:58:35 +03:00
olasaadi
af7d615628 fix 2022-07-04 12:55:58 +03:00
natali
50317a8d67 fix for keras model check_and_transform_label_format requires nb_classes 2022-07-03 09:59:41 +03:00
abigailgold
c6eb553a9f
Blackbox predict method (#43) 
* Support output probabilities
* Support black box classifier with predict method
* Update requirements (security alert #1)
 2022-06-30 18:23:53 +03:00
Natalia Razinkov
bb224cd3dd
Bug fix for PytorchData dataset 2022-06-26 15:15:51 +03:00
Shlomit Shachor
1c4b963add
Wrappers no train (#40) 
1) Handle train None in Data
2) Update BB Classifier to handle None either for train or test (x or y)
 2022-06-26 14:43:22 +03:00
olasaadi
21cba95a28 fix 2022-06-06 14:32:34 +03:00
olasaadi
c954f53ad7 fix 2022-06-06 14:02:40 +03:00
olasaadi
302d0c4b8c update 2022-06-02 15:25:07 +03:00