redshiftzero
redshiftzero
We want to know in a realistic scenario - i.e. one that incorporates the effect of the class imbalance - how effective these attacks are in terms of true and...
We don't really know the base rate of SecureDrop usage: yay anonymity. However, this means that in order to see how many users an attacker would correctly and incorrectly flag...
The "sorter" tells us the state of onionspace based on public directories of onion services. We should ensure that this is being executed every night (via cron) such that the...
We have a very imbalanced machine learning problem, where we have far fewer SecureDrop users than non-SecureDrop users. There are many ways of handling this situation - including oversampling the...
Many of our features are not very useful. We should include a first step of feature selection before passing the features matrix to the classifier. This could be something simple,...
Right now we generate a ROC curve that is averaged over all k-folds, but we don't save the FPR and TPR in the database in `models.undefended_frontpage_attacks`. We should do that...
Rewrite the burst generation code currently performed in `FeatureStorage.create_bursts()` in `features.py` in SQL such that feature generation is fast and scalable
The task here is to update these bindings for upstream changes. This can be done a few commits at a time to make it easier to review. The process here...
does it make sense to and is it possible to create a minimal facade API for use in python such that only rust is handling secrets? the idea here is...
We should scan source interfaces and automatically send emails to admins upon multiple failed scans (we'll still want to retry the scan several times before sending an email due to...