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

308 commits

This branch
This branch
All branches
Author SHA1 Message Date
A. Unique TensorFlower
5cd2439401 Remove calls to _dp_sum_query.set_batch_size in dp_optimizer.py, as no method with that name exists for objects of class QueryWithLedger. 
PiperOrigin-RevId: 259858031
 2019-07-24 18:08:35 -07:00
A. Unique TensorFlower
28fd879864 Merge pull request #57 from jvmancuso:qadapt-nest-ver 
PiperOrigin-RevId: 259592947
 2019-07-23 12:56:31 -07:00
Christopher Choquette Choo
9b08c163e0
Merge pull request #5 from georgianpartners/bolton 
Adding README to explain Bolton Module.
 2019-07-22 11:31:09 -04:00
Christopher Choquette Choo
968ea70060 Fixing typos. 2019-07-22 11:30:55 -04:00
Christopher Choquette Choo
7785436cf3 Minor changes to README 2019-07-22 11:30:29 -04:00
Christopher Choquette Choo
0082c9ba76 Minor doc change and adding README file explaining Bolton Method. 2019-07-22 11:27:53 -04:00
jvmancuso
3072c86c79 find nest module based on TF version for quantile_adaptive_clip_sum_query.py 2019-07-20 10:43:48 -04:00
Nicolas Papernot
3de1fcd829 add pylint to README 
PiperOrigin-RevId: 259029555
 2019-07-19 13:41:07 -07:00
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
A. Unique TensorFlower
98723b9c3a Added rdp_accountant dependency to privacy/BUILD. 
PiperOrigin-RevId: 258657061
 2019-07-17 15:44:16 -07:00
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
Galen Andrew
973a1759aa Remove unused global_state reference from initial_sample_state. 
global_state is never used in any of our existing DPQueries, and we don't have any compelling use case.

PiperOrigin-RevId: 255480537
 2019-06-27 14:37:49 -07:00
Nicolas Papernot
6171474465 harmonize analysis parameters with current DPSGD API 
PiperOrigin-RevId: 255080643
 2019-06-25 17:06:01 -07:00
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
b120d9c5d8 Changes for pylint. 2019-06-19 11:14:02 -04:00
Christopher Choquette Choo
56e16f0a15 Minor changes + tutorial 2019-06-19 11:04:18 -04:00
cchoquette
738a7ee8e4
Merge pull request #2 from tensorflow/master 
Logistic regression for mnist with new privacy analysis.
 2019-06-19 10:51:11 -04:00
Christopher Choquette Choo
f41be2c598 Bolton implementation and unit tests. Has two pre-implemented loss functions. 2019-06-19 10:46:30 -04:00
Christopher Choquette Choo
ed7fa73a99 Update Huber loss regularization term and some small changes across loss parameters. 2019-06-17 14:46:04 -04:00
Christopher Choquette Choo
935d6e8480 Bolton created as optimizer with context manager usage. 
Unit tests included.
Additional loss functions TBD.
 2019-06-17 13:25:30 -04:00
Christopher Choquette Choo
ec18db5ec5 Working bolton model without unit tests. 
-- moving to Bolton Optimizer
Model is now just a convenient wrapper and example for users.
Optimizer holds ALL Bolton privacy requirements.
Optimizer is used as a context manager, and must be passed the model's layers.
Unit tests incomplete, committing for visibility into the design.
 2019-06-13 01:01:31 -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
Christopher Choquette Choo
751eaead54 Working bolton model without unit tests. 
-- update to include pull request changes
changes include:
parameter renaming,
changing to mixin,
moving model to compile,
additional tests,
fixing huber loss
 2019-06-10 16:11:47 -04:00
Christopher Choquette Choo
5f46927747 Working bolton model without unit tests. 2019-06-05 17:06:02 -04:00
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
Galen Andrew
7636945566 Cast to ensure record of NoPrivacyAverageQuery is float for compatibility with sample_state. 
PiperOrigin-RevId: 249909614
 2019-05-24 15:28:39 -07:00
Steve Chien
15c07250a1 Add dtype=tf.int32 to TensorBuffer capacity and current size. 
PiperOrigin-RevId: 249908717
 2019-05-24 15:22:43 -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
0efb23afcb Changing initial capacity for the ledger to smaller values. (+ restoring compatibility with Python 2) 
PiperOrigin-RevId: 249292683
 2019-05-21 11:38:27 -07:00
Ilya Mironov
a94dc626b1 Specifying minimal TF version required (currently 1.13, due to dependency on the train module). 
PiperOrigin-RevId: 248809713
 2019-05-17 16:39:48 -07:00
Galen Andrew
7992006077 Add quantile_adaptive_clip_sum_query to privacy package. 
PiperOrigin-RevId: 248617353
 2019-05-16 15:56:16 -07:00
Galen Andrew
3908429796 Make DPQuery classes (almost) completely functional: the only state from the initializer that is used gets pushed into the initial_global_state. 
PiperOrigin-RevId: 248424593
 2019-05-15 16:06:37 -07:00
Steve Chien
17fefb3895 Remove tf.function annotation from quantile_adaptive_clip_sum_query.py that was causing import error. 
PiperOrigin-RevId: 248236331
 2019-05-14 16:40:55 -07:00
Galen Andrew
aaf029edad Add quantile_adaptive_clip_sum_query which dynamically adjusts the clipping norm so a specified fraction of records per sample are clipped. 
PiperOrigin-RevId: 248201320
 2019-05-14 13:35:29 -07:00
Galen Andrew
1d1a6e087a Extensions to DPQuery and subclasses. 
1. Split DPQuery.accumulate_record function into preprocess_record and accumulate_preprocessed_record.
2. Add merge_sample_state function.
3. Add default implementations for some functions in DPQuery, and add base class SumAggregationDPQuery that implements some more. Only get_noised_result is still abstract.
4. Enforce that all states and parameters used as inputs and outputs to DPQuery functions are nested structures of tensors by replacing numbers with constants and Nones with empty tuples.

PiperOrigin-RevId: 247975791
 2019-05-13 11:28:56 -07:00
Steve Chien
82852c0e71 Add comments explaining the relationship between ML terminology and DP terminology. 
PiperOrigin-RevId: 246926753
 2019-05-06 17:12:24 -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
Steve Chien
098940bf1b Very minor formatting change. 
PiperOrigin-RevId: 246596295
 2019-05-03 16:41:38 -07:00
Steve Chien
28639ba0a8 Allow tensor buffers to automatically resize as needed. 
PiperOrigin-RevId: 246594454
 2019-05-03 16:30:02 -07:00
Steve Chien
beb86c6e18 Update PrivacyLedger and DPOptimizer to make certain arguments optional. 
PiperOrigin-RevId: 246235646
 2019-05-01 18:07:32 -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