apunkt/ai-privacy-toolkit
1
0
Fork 0
mirror of https://github.com/IBM/ai-privacy-toolkit.git synced 2026-06-08 15:05:13 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
150 commits 9 branches 4 tags 2.3 MiB
Commit graph

114 commits

Author SHA1 Message Date
Maya Anderson
c71f8f6e2f Fix references in README 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-19 15:24:54 +02:00
Maya Anderson
89bc9f0989 Return a more specific class in calculate_privacy_score(). Add more type hints and comments. Make method static. 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-19 15:24:54 +02:00
Maya Anderson
4c7cad86df Fix README references, and those in other comments 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-19 10:34:56 +02:00
Maya Anderson
d77cdf0da3 Add README 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-17 11:46:05 +02:00
Maya Anderson
39dc8026e6 Rename attack reference from mgr to attack 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-17 11:46:05 +02:00
Maya Anderson
80bec0c45b Add a risk score to the base class DatasetAttackScore, so that every implementation could set it based on its specific values. 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-17 11:46:05 +02:00
Maya Anderson
8a4df5a4a2 Additional review comments - moved result to score base class 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-13 00:30:18 +02:00
Maya Anderson
4988fea08c Rename DatasetAttackPerRecordKnnProbabilities => DatasetAttackMembershipKnnProbabilities 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-09 23:17:37 +02:00
Maya Anderson
a122976807 Address review comments - make dataset_name optional, fix filename. Fix score serialization - don't serialize the result. 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-09 22:49:57 +02:00
Maya Anderson
3ae64054f8 Unite the interface so that the main method assess_privacy always returns a score, but the score may also contain an attack result, which can be further analyzed 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-08 15:15:00 +02:00
Maya Anderson
69a9a8fa2b Rename and move knn_learner in attack strategy utils for readability according to review 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-08 10:31:09 +02:00
Maya Anderson
185d9b9664 Fix share calculation, and find only 1 KNN per sample for it 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-08 00:27:16 +02:00
Maya Anderson
e5f6089b23 Rename gan_leaks=>per_record_knn_probabilities and holdout=>whole_dataset_knn_distance 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-08 00:27:16 +02:00
Maya Anderson
e7e725ea80 Address review comments: 
extract common code, add comments, change ellipsis to pass

Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-08 00:27:16 +02:00
Maya Anderson
3f9271b225 Add Dataset assessment module 
Signed-off-by: Maya Anderson <mayaa@il.ibm.com>
 2023-03-06 10:01:45 +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
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
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
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