adversarial-robustness-toolbox
adversarial-robustness-toolbox copied to clipboard
Create sample_from_sphere_or_ball
The function here samples uniformly from either the ball or the sphere with a given norm with possibly different radii
Description
Please include a summary of the change, motivation and which issue is fixed. Any dependencies changes should also be included.
Fixes # (issue)
Type of change
Please check all relevant options.
- [x] Improvement (non-breaking)
- [x] Bug fix (non-breaking)
- [x] New feature (non-breaking)
- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
- [ ] This change requires a documentation update
Testing
Please describe the tests that you ran to verify your changes. Consider listing any relevant details of your test configuration.
- [ ] Test A
- [ ] Test B
Test Configuration:
- OS
- Python version
- ART version or commit number
- TensorFlow / Keras / PyTorch / MXNet version
Checklist
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my own code
- [ ] I have commented my code
- [ ] I have made corresponding changes to the documentation
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my feature works
- [ ] New and existing unit tests pass locally with my changes
Codecov Report
Merging #1804 (b7f0686) into dev_1.12.0 (9fa6749) will decrease coverage by
0.00%
. The diff coverage is100.00%
.
@@ Coverage Diff @@
## dev_1.12.0 #1804 +/- ##
==============================================
- Coverage 85.57% 85.57% -0.01%
==============================================
Files 271 271
Lines 23048 23046 -2
Branches 4103 4102 -1
==============================================
- Hits 19723 19721 -2
Misses 2316 2316
Partials 1009 1009
Impacted Files | Coverage Δ | |
---|---|---|
art/attacks/evasion/sign_opt.py | 86.49% <ø> (ø) |
|
art/estimators/certification/deep_z/pytorch.py | 87.50% <ø> (ø) |
|
...certification/derandomized_smoothing/tensorflow.py | 85.00% <100.00%> (ø) |
|
art/attacks/evasion/dpatch.py | 91.25% <0.00%> (-0.11%) |
:arrow_down: |
This pull request introduces 1 alert when merging a5f0ff2f980ca2e7bc26319f66e8e1ffcef9e5c9 into 9bc3b269e3cb7cb906603704f895fcddf8b1ac72 - view on LGTM.com
new alerts:
- 1 for Module is imported more than once
This pull request introduces 1 alert when merging dbe994fa46e07392d7eba335700ac1c36c729c6e into 9bc3b269e3cb7cb906603704f895fcddf8b1ac72 - view on LGTM.com
new alerts:
- 1 for Module is imported more than once
This pull request introduces 1 alert when merging b7f0686219a47f1cfb3f709a1e8834d6c106f115 into 9bc3b269e3cb7cb906603704f895fcddf8b1ac72 - view on LGTM.com
new alerts:
- 1 for Module is imported more than once
Hi @nmegiddo Thank you very much for implementing the correct sampling from norm spheres or balls! I pull this PR to a dev branch to move the function to art.utils
.