Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / tensorflow/privacy issues and pull requests
#401 - Fix dependencies required by `privacy_tests`.
Pull Request -
State: closed - Opened by copybara-service[bot] almost 2 years ago
#376 - First implementation of the fast gradient clipping algorithm.
Pull Request -
State: closed - Opened by copybara-service[bot] almost 2 years ago
#355 - tensorflow privacy requires numpy ~= 1.21 which is not compatible with python 11
Issue -
State: open - Opened by jim-smith almost 2 years ago
#352 - Potential bug using kernel regularizer
Issue -
State: open - Opened by JustinNoland24 almost 2 years ago
#349 - Insecure Random Number Generator
Issue -
State: open - Opened by gonzalo-munillag almost 2 years ago
- 1 comment
#348 - Bugfix.
Pull Request -
State: closed - Opened by copybara-service[bot] almost 2 years ago
#347 - Allows slicing by custom indices.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#345 - Correct imports of keras loss utils
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#344 - CVE-2007-4559 Patch
Pull Request -
State: open - Opened by TrellixVulnTeam about 2 years ago
- 1 comment
#343 - Remove pfor dependency in BUILD file, and strengthen unit tests for clip_and_aggregate_gradients.py.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#342 - Efficient DP optimizers for sparse models.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#341 - Add tests for common use patterns.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#340 - Calls epsilon computation in MIA.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#339 - Ensures DPOptimizer objects can be serialized by TensorFlow.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#338 - Remove dependence on six in clip_and_aggregate_gradients.py.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#337 - Bump version for release.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#336 - Clip (per-example) and aggregate gradients.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#335 - Implement initial_sample_state for TreeRangeSumQuery.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#334 - Fix SumAggregationDPQuery's initial_sample_state raising a ValueError when called on TensorSpec.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#333 - Add DPEvent to the state in DifferentiallyPrivateFactory's next_fn. This requires implementing initial_sample_state in TreeRangeSumQuery for tests to pass.
Pull Request -
State: open - Opened by copybara-service[bot] about 2 years ago
#332 - Changes `DPOptimizerClass` to generically accept and use any `dp_sum_query`.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#330 - Adds a utility function for formating list into string.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#326 - Add functions to derive epsilon lower bounds.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#324 - Make Keras optimizers generic.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#302 - Adds DP-FTRL via tree aggregation optimizer `DPFTRLTreeAggregationOptimizer`.
Pull Request -
State: closed - Opened by copybara-service[bot] about 2 years ago
#287 - ValueError: Dimension size must be evenly divisible by 250 but is 1 for '{{node Reshape}}
Issue -
State: open - Opened by codebecker over 2 years ago
- 3 comments
#247 - AttributeError: 'Conv2D' object has no attribute 'apply'
Issue -
State: open - Opened by JosephMPedersen over 2 years ago
- 2 comments
#214 - ValueError: None values not supported.
Issue -
State: open - Opened by RANCE-sama over 2 years ago
#185 - Add NeuraCrypt attack code to research directory
Pull Request -
State: closed - Opened by carlini almost 3 years ago
#180 - ValueError: Dimension size must be evenly divisible by 10 but is 1 for '{{node training/Reshape}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32](loss/mul, training/Reshape/shape)' with input shapes: [], [2] and with input tensors computed as partial shapes: input[1] = [10,?]
Issue -
State: open - Opened by jaalmoes almost 3 years ago
- 4 comments
#177 - Missing of dataset for dplstm in tutorials
Issue -
State: open - Opened by Antoine-ls about 3 years ago
- 3 comments
#122 - The link is disabled in `privacy/research/pate_2018/ICLR2018/download.py`
Issue -
State: open - Opened by Billy1900 about 4 years ago
- 2 comments
#106 - AssertionError: compute_gradients() on the differentially private optimizer was not called.
Issue -
State: open - Opened by mayankshah1607 over 4 years ago
- 9 comments
#92 - Issue with variational autoencoder loss and DP training
Issue -
State: open - Opened by khalidaskia almost 5 years ago
- 4 comments
#85 - Reproducing Figure 2 from the DP-SGD paper (Abadi et al., 2016)
Issue -
State: closed - Opened by AndreiBarsan almost 5 years ago
- 11 comments