ruby/tensorflow_privacy
1
0
Fork 0
forked from 626_privacy/tensorflow_privacy
Code Pull requests Activity
233 commits 2 branches 0 tags 3.1 MiB
Commit graph

77 commits

Author SHA1 Message Date
Yanhua Sun
856eda3aa1 Explicitly replace "import tensorflow" with "tensorflow.compat.v1" 
PiperOrigin-RevId: 290355582
 2020-02-07 10:18:46 -08:00
A. Unique TensorFlower
1a448b4272 Document how to set delta. Document orders list in eps computation. 
PiperOrigin-RevId: 289514598
 2020-01-13 14:07:14 -08:00
Nicolas Papernot
8d185c81c7 fix language in colab 
PiperOrigin-RevId: 281372393
 2019-11-19 14:39:58 -08:00
Steve Chien
28d6db4c92 Update Colab to advise users to use a GPU. 
PiperOrigin-RevId: 277761946
 2019-10-31 11:14:57 -07:00
Steve Chien
d69879d360 Changes to make Tensorflow Privacy compatible with TF 2.0. 
PiperOrigin-RevId: 277561553
 2019-10-30 12:33:02 -07:00
Steve Chien
8a80c1a745 Suppress warnings in Colab 
PiperOrigin-RevId: 277393252
 2019-10-29 16:49:32 -07:00
Steve Chien
853ec20b52 Specify TF 1.x in Colab. 
PiperOrigin-RevId: 277385438
 2019-10-29 16:07:28 -07:00
Steve Chien
cad86b925e Update link in Colab button at top of page. 
PiperOrigin-RevId: 276752314
 2019-10-25 13:44:44 -07:00
anirudh161
596bba431d
Fix Colab link and remove link to tensorflow.org 2019-10-24 17:00:08 -07:00
anirudh161
eb5666b16b
Fix Colab link 2019-10-24 15:36:03 -07:00
anirudh161
ab67fcc455
Change Colab Link 2019-10-24 15:30:27 -07:00
anirudh161
41910b10e9 Add DPSGD-Keras Tutorial 2019-10-24 15:25:13 -07:00
Steve Chien
1ce8cd4032 Restructure TF Privacy to be more in line with other repos in the TF ecosystem. 
PiperOrigin-RevId: 274674077
 2019-10-14 15:29:52 -07:00
Steve Chien
0776ed124b Add link to paper on Renyi Differential Privacy. 
PiperOrigin-RevId: 267412177
 2019-09-05 11:15:27 -07:00
A. Unique TensorFlower
0e84af1e69 Merge pull request #70 from georgianpartners:master 
PiperOrigin-RevId: 265056745
 2019-08-23 08:06:16 -07:00
A. Unique TensorFlower
602b1c3f37 Update tfds.load() callers to specify shuffle_files=True when necessary. 
PiperOrigin-RevId: 264803647
 2019-08-22 04:02:08 -07:00
Christopher Choquette Choo
ce20982db0 Merge remote-tracking branch 'origin/master' 2019-08-21 22:57:51 -04:00
Christopher Choquette Choo
18ce9c2335 Stable version for tf2.0a0, b0. 2019-08-21 22:57:35 -04:00
Nicolas Papernot
c7ca8092fb Introduce vectorized DP optimizer 
PiperOrigin-RevId: 262414086
 2019-08-08 12:56:28 -07:00
A. Unique TensorFlower
9fe5e91de4 Merge pull request #53 from georgianpartners:master 
PiperOrigin-RevId: 260990063
 2019-07-31 13:44:12 -07:00
Christopher Choquette Choo
4bd0ad482a Refactoring bolton to bolt_on from package refactor for comments + strings. 2019-07-31 10:55:25 -04:00
Christopher Choquette Choo
c0bd19365b Refactoring bolton package to bolt_on only in code usages. 2019-07-31 10:52:41 -04:00
Christopher Choquette Choo
2065f2b16a Code style and documentation changes. 2019-07-30 15:12:22 -04:00
Christopher Choquette Choo
92f97ae32c Fixing missing args. 2019-07-27 13:54:19 -04:00
npapernot
0317ce8077 print 2019-07-25 16:17:56 +00:00
npapernot
8974a95b9a more fixes 2019-07-25 16:13:32 +00:00
npapernot
8e6bcf9b4a many fixes 2019-07-25 15:37:54 +00:00
Christopher Choquette Choo
5857e838ba
Merge pull request #4 from georgianpartners/bolton 
Ensuring pylint is 10/10
 2019-07-18 15:07:52 -04:00
Christopher Choquette Choo
c05c2aa0d4 Ensuring pylint is 10/10 2019-07-18 15:04:35 -04:00
Christopher Choquette Choo
eab43e8294
Merge pull request #3 from georgianpartners/bolton 
Code review changes
 2019-07-16 20:02:31 -04:00
Nicolas Papernot
bb7956ed7e fix keras typo 
PiperOrigin-RevId: 258434656
 2019-07-16 13:59:14 -07:00
Christopher Choquette Choo
b03eb6914b Code review changes: Fixed doc string spacing, copyrighting, and changed the jupyter file to a python script. 2019-07-16 10:33:57 -04:00
Ilya Mironov
45bcb3a0e4 Adding privacy analysis to the Logistic Regression for MNIST tutorial. 
PiperOrigin-RevId: 254815428
 2019-06-24 12:50:08 -07:00
cchoquette
0b244f0e47
Working bolton model without unit tests. (#1) 
Bolton implementation including:
- Bolton Model wrapper for using Bolton method
- Bolton Optimizer encompassing all privacy components
- Introduction of Strongly Convex Loss functions with 2 pre-implemented
- Unit tests for the above.
 2019-06-19 11:21:50 -04:00
Christopher Choquette Choo
3080b654b5 Minor changes to function arguments 2019-06-19 11:18:42 -04:00
Christopher Choquette Choo
56e16f0a15 Minor changes + tutorial 2019-06-19 11:04:18 -04:00
A. Unique TensorFlower
2b97c7c735 Logistic regression for mnist with new privacy analysis. 
PiperOrigin-RevId: 252743967
 2019-06-11 18:58:56 -07:00
Galen Andrew
d5dcfec745 Remove set_denominator functions from DPQuery and make QueryWithLedger easier to use. 
set_denominator was added so that the batch size doesn't need to be specified before constructing the optimizer, but it breaks the DPQuery abstraction. Now the optimizer uses a GaussianSumQuery instead of GaussianAverageQuery, and normalization by batch size is done inside the optimizer.

Also instead of creating all DPQueries with a PrivacyLedger and then wrapping with QueryWithLedger, it is now sufficient to create the queries with no ledger and QueryWithLedger will construct the ledger and pass it to all inner queries.

PiperOrigin-RevId: 251462353
 2019-06-04 10:14:32 -07:00
Nicolas Papernot
a06bc6c99b fix imports for v1 and make the versioning more explicit through LooseVersion 
PiperOrigin-RevId: 249732562
 2019-05-23 15:57:08 -07:00
Ilya Mironov
9cece21d92 Clean-up pass to eliminate warnings: replacing deprecated endpoints with recommended versions and annotating test sizes. 
PiperOrigin-RevId: 246901723
 2019-05-06 14:50:23 -07:00
Ilya Mironov
85280ab568 Removing max_samples and max_queries from the tutorial. 
PiperOrigin-RevId: 246850557
 2019-05-06 10:30:35 -07:00
Nicolas Papernot
c09ec4c22b minor fixes to improve tf 1 and 2 compatibility 
PiperOrigin-RevId: 246008822
 2019-04-30 13:22:57 -07:00
Nicolas Papernot
febafd830d update API calls for TF2 
PiperOrigin-RevId: 245817981
 2019-04-29 14:00:40 -07:00
A. Unique TensorFlower
ab466b156c Check batch_size % microbatches = 0 and calculate privacy budget only when dpsgd is set. 
PiperOrigin-RevId: 244949900
 2019-04-23 16:40:33 -07:00
Ilya Mironov
a3e03f773e Adding a paragraph to the walk-through on how to choose RDP orders. Plus deleting empty lines in rdp_accountant.py. Fixing issue #47. 
PiperOrigin-RevId: 244467825
 2019-04-19 21:50:49 -07:00
Tim Garnsey
aeb6a94b59 added a ledger during optimizer instantiation to the language model tutorial 2019-04-17 12:52:08 +10:00
Steve Chien
3dc2b398d2 Closes #41 
PiperOrigin-RevId: 241786994
 2019-04-03 12:48:25 -07:00
Galen Andrew
9106a04e2c Use PrivacyLedger for privacy accounting. 
Prior to this change the PrivacyLedger is running to keep a log of private queries, but the ledger is not actually used to compute the (epsilon, delta) guarantees. This CL adds a function to compute the RDP directly from the ledger.

Note I did verify that the tutorial builds and runs with the changes and for the first few iterations prints the same epsilon values as before the change.

PiperOrigin-RevId: 241063532
 2019-03-29 15:31:32 -07:00
Nicolas Papernot
8507094f2b add walkthrough MD 
PiperOrigin-RevId: 241016765
 2019-03-29 11:24:36 -07:00
Nicolas Papernot
03050adb27 adding scratch for walkthrough blog post 
PiperOrigin-RevId: 240425310
 2019-03-26 14:16:27 -07:00