Fix domain privacy leak #19
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sofiane87
force-pushed
the
18-privacy-leak-via-data-dependent-domain-inference
branch
from
5f9052a to
b9a54bd
Compare
☂️ Python Coverage
Overall Coverage
New FilesNo new covered files... Modified Files
|
Signed-off-by: sofiane87 <sofiane-mahiou@hotmail.fr> Add Sphinx documentation and Read the Docs configuration Ensure domain is always required Add comment in README
sofiane87
force-pushed
the
18-privacy-leak-via-data-dependent-domain-inference
branch
from
229d71c to
8f7b575
Compare
Signed-off-by: sofiane87 <sofiane-mahiou@hotmail.fr>
sofiane87
force-pushed
the
18-privacy-leak-via-data-dependent-domain-inference
branch
from
a7a17dc to
68e7b03
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR addresses issue #18 by making the data domain a requirement within the core models.
It is noteworthy that in the intended use of the models is through the generative pipeline layer, which combines preprocessing and model fitting/generation, to ensure that no unintended privacy leakage occurs. While the models can be used directly, doing so requires explicitly providing the data domain in order to maintain the same privacy guarantees.