626_privacy/tensorflow_privacy
2
0
Fork 1
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions
856 commits 2 branches 0 tags 3.1 MiB
Commit graph

856 commits

This branch
This branch
All branches
Author SHA1 Message Date
Galen Andrew
4cb0a11c4b Automated rollback of commit db292fc5d8 
PiperOrigin-RevId: 462171425
 2022-07-20 10:16:48 -07:00
Steve Chien
38fe4aa984 Changes to prepare for release of v0.8.1. 
Update WORKSPACE, setup.py, and requirements.txt to latest dp-accounting library release.

Update scipy version in setup.py.

Update version to 0.8.1.

PiperOrigin-RevId: 461944491
 2022-07-19 12:22:07 -07:00
A. Unique TensorFlower
2b5d5b6ef5 Add Positive Predictive Value as a metric for membership attack models performance on imbalanced data. 
PiperOrigin-RevId: 461390184
 2022-07-16 16:30:53 -07:00
Shuang Song
328795aa36 Add assert that the training is private for TF1 vectorized optimizer. 
In Keras training in TF 2.0+, compute_gradients() is not called but apply_gradients() is called. W/o calling compute_gradients() dp gradient is not computed, and a normal gradient is used.

PiperOrigin-RevId: 461021412
 2022-07-14 12:15:00 -07:00
Michael Reneer
64c6b5ea25 Revert scipy dependency. 
PiperOrigin-RevId: 460957101
 2022-07-14 07:45:03 -07:00
A. Unique TensorFlower
1d002aa49c Increment the differential privacy accounting Bazel dependency to a version that supports mechanism calibration. 
PiperOrigin-RevId: 460539211
 2022-07-12 13:29:27 -07:00
A. Unique TensorFlower
e826ec717a Switch from a git_repository rule to http_archive for the DP accounting Bazel dependency. This is preferred, per https://docs.bazel.build/versions/main/external.html#repository-rules, to avoid depending on the system git (the HTTP downloader is build into Bazel). 
Also use the strip_prefix option to only pull in the accounting WORKSPACE, not the top-level Google DP project WORKSPACE. This allows us to align the import statements to work both when pulling in the `dp_acounting` dependency via Bazel and pip.

PiperOrigin-RevId: 459807060
 2022-07-08 12:07:17 -07:00
Michael Reneer
8b698a7fea Update build_pip_package script to use the built in Python virtual environment tool. 
See https://docs.python.org/3/library/venv.html for more information

PiperOrigin-RevId: 459806458
 2022-07-08 12:05:21 -07:00
Michael Reneer
27c07fa7b8 Update the TFP requirements. 
PiperOrigin-RevId: 459806353
 2022-07-08 12:04:04 -07:00
A. Unique TensorFlower
eaa7354f00 Internal change. 
PiperOrigin-RevId: 459620579
 2022-07-07 15:48:25 -07:00
Steve Chien
24f80e8c76 Increase scipy version to 1.7.1. 
PiperOrigin-RevId: 459371512
 2022-07-06 16:27:01 -07:00
Michael Reneer
94beccf10e Automated rollback of commit e32766cc73 
PiperOrigin-RevId: 458498524
 2022-07-01 10:34:33 -07:00
A. Unique TensorFlower
e32766cc73 Automated rollback of commit b16a0abf1c 
PiperOrigin-RevId: 458478847
 2022-07-01 08:52:40 -07:00
Michael Reneer
b16a0abf1c Update TFPs dp_accounting dependency. 
PiperOrigin-RevId: 458307242
 2022-06-30 13:57:42 -07:00
Galen Andrew
22b92a61ca Update to newest commit of differential_privacy. 
PiperOrigin-RevId: 458275483
 2022-06-30 11:39:08 -07:00
A. Unique TensorFlower
c665281c55 Implementation of Differentially Private Logistic Regression. 
PiperOrigin-RevId: 458266079
 2022-06-30 11:01:02 -07:00
Galen Andrew
77d962e0fc Use DP library's calibrate_dp_mechanism function to compute noise multiplier. 
calibrate_dp_mechanism is in dp_accounting's top level symbols, so after this change we can replace all of the dependencies on DP accounting subpackages with dp_accounting.

Tested by verifying that the resulting noise multiplier is the same before and after change when running all tests in multinomial_logistic_test.

PiperOrigin-RevId: 458235745
 2022-06-30 08:47:54 -07:00
Markus Kunesch
9383743252 Update attrs dependency in requirements.txt to match setup.py. 
PiperOrigin-RevId: 456986050
 2022-06-24 04:59:18 -07:00
Michael Reneer
adce0fdfc0 Update TFPs attrs dependency to version 21.4.0. 
PiperOrigin-RevId: 455655859
 2022-06-17 11:09:29 -07:00
Galen Andrew
295e533e22 Internal change. 
PiperOrigin-RevId: 455191950
 2022-06-15 12:23:30 -07:00
Steve Chien
7a5f4eddb8 Internal change. 
PiperOrigin-RevId: 455173202
 2022-06-15 11:05:05 -07:00
Galen Andrew
db292fc5d8 Automated rollback of commit bb1b7a6a46 
PiperOrigin-RevId: 454995196
 2022-06-14 17:27:35 -07:00
Galen Andrew
bb1b7a6a46 Remove deprecated rdp_accountant. Please use RdpAccountant from the differential_privacy library. 
PiperOrigin-RevId: 454964256
 2022-06-14 15:02:34 -07:00
Galen Andrew
c4fea75675 Remove differential_privacy dp_event classes from TFP top-level symbols. 
PiperOrigin-RevId: 454238513
 2022-06-10 14:09:46 -07:00
Galen Andrew
125f82707a Migrate dependency of tree_aggregation_accountant_test on rdp_accountant to differential_privacy. 
PiperOrigin-RevId: 453989532
 2022-06-09 12:44:20 -07:00
Matthew Jagielski
6c0cc858e0 Add word2vec attack example to attack library. 
PiperOrigin-RevId: 453489150
 2022-06-07 11:46:55 -07:00
Galen Andrew
fca208e514 Finish migration of mnist_lr_tutorial to use differential_privacy library. 
PiperOrigin-RevId: 453258715
 2022-06-06 12:32:54 -07:00
Galen Andrew
97f5c2fdfb Update to use new Google differential privacy gethub commit. 
PiperOrigin-RevId: 452616485
 2022-06-02 14:02:10 -07:00
Mark Daoust
222c688210 Fix colab and github links. 
PiperOrigin-RevId: 452587969
 2022-06-02 11:47:02 -07:00
A. Unique TensorFlower
7d522e9273 Remove an indentation in a comment. 
PiperOrigin-RevId: 451008704
 2022-05-25 14:01:16 -07:00
A. Unique TensorFlower
5461f911a6 Bugfixes: 
1. Child classes of 'TrainedAttacker' now have a 'backend' parameter, so require an __init__() method.

PiperOrigin-RevId: 451005298
 2022-05-25 13:46:30 -07:00
A. Unique TensorFlower
95e527acfb Support models with unconnected layers and gradients when training using a DP vectorized optimizer. 
PiperOrigin-RevId: 450659644
 2022-05-24 05:36:58 -07:00
Galen Andrew
5509adb296 Change README example to use Google DP for accounting instead of deprecated privacy/analysis/rdp_accountant functions. 
PiperOrigin-RevId: 449820802
 2022-05-19 13:29:57 -07:00
Steve Chien
f739f45299 Add .bazelversion file. 
PiperOrigin-RevId: 448082134
 2022-05-11 14:14:48 -07:00
A. Unique TensorFlower
97eec1a8e3 COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/privacy/pull/234 from ftramer:truth_serum fe44a0713952ef1615abf032947082eb5c082836 
PiperOrigin-RevId: 447573314
 2022-05-09 15:06:13 -07:00
Steve Chien
137f795352 Remove license from lr_acc.json file. 
PiperOrigin-RevId: 446850420
 2022-05-05 16:47:13 -07:00
Galen Andrew
afe676135e Migrate lm_dpsgd_tutorial from deprecated TFP rdp_accountant to Google DP. 
PiperOrigin-RevId: 446846972
 2022-05-05 16:31:54 -07:00
A. Unique TensorFlower
65eadd3a02 Enable parallel processing in the Scikit-Learn models. 
Add support for configuring the parallel processing backend for Scikit-Learn while setting up the attack models.

PiperOrigin-RevId: 446844669
 2022-05-05 16:21:15 -07:00
A. Unique TensorFlower
7eea74a6a1 COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/privacy/pull/230 from npapernot:hyperparam 8835b9c4072e3e598aa49d605e7643a2c2e65988 
PiperOrigin-RevId: 446832781
 2022-05-05 15:38:47 -07:00
A. Unique TensorFlower
930c4d13e8 Handle the case when the data comes from a multilabel classification problem but the provided samples happen to have just one positive label per sample. 
PiperOrigin-RevId: 445468067
 2022-04-29 11:36:47 -07:00
Galen Andrew
e0ab480e3d Use updated Google differential_privacy library. 
PiperOrigin-RevId: 445189891
 2022-04-28 10:36:04 -07:00
Galen Andrew
81d5880702 Migrate accounting in tutorials to Google DP. 
PiperOrigin-RevId: 444993855
 2022-04-27 16:09:27 -07:00
Fabien Hertschuh
d47cc695cd Consistently import all estimator symbols via tensorflow_estimator as opposed to using tensorflow.estimator for some symbols. 
PiperOrigin-RevId: 443417581
 2022-04-21 10:36:59 -07:00
Yilei Yang
de585e5619 Remove unused comments related to Python 2 compatibility. 
PiperOrigin-RevId: 443383047
 2022-04-21 08:20:08 -07:00
Galen Andrew
868cf54470 Deprecates implementations of RDP accounting from tensorflow_privacy in favor of differential_privacy. 
PiperOrigin-RevId: 443177278
 2022-04-20 13:25:48 -07:00
A. Unique TensorFlower
ee35642b90 Add multi-label support for Tensorflow Privacy membership attacks. 
PiperOrigin-RevId: 443176652
 2022-04-20 13:23:26 -07:00
Galen Andrew
e14618fe7c Remove DpEvent from tensorflow_privacy which has been migrated to Google DP libraries. 
PiperOrigin-RevId: 441490619
 2022-04-13 08:40:52 -07:00
Galen Andrew
34ad9dbedc Automated rollback of commit 7e89dad685 
PiperOrigin-RevId: 441245348
 2022-04-12 11:34:14 -07:00
A. Unique TensorFlower
7e89dad685 Delete TF Privacy fork of the Google DP accounting API. 
PiperOrigin-RevId: 440992901
 2022-04-11 14:12:46 -07:00
A. Unique TensorFlower
34f8774dad Migrate more references to dp_event to Google DP libraries. 
PiperOrigin-RevId: 440230682
 2022-04-07 16:39:38 -07:00