mirror of
https://github.com/tutao/tutanota.git
synced 2025-12-08 06:09:50 +00:00
5293be6a4a
We sync the spam training data encrypted through our server to make sure that all clients for a specific user behave the same when classifying mails. Additionally, this enables the spam classification in the webApp. We compress the training data vectors (see clientSpamTrainingDatum) before uploading to our server using SparseVectorCompressor.ts. When a user has the ClientSpamClassification enabled, the spam training data sync will happen for every mail received. ClientSpamTrainingDatum are not stored in the CacheStorage. No entityEvents are emitted for this type. However, we retrieve creations and updates for ClientSpamTrainingData through the modifiedClientSpamTrainingDataIndex. We calculate a threshold per classifier based on the dataset ham to spam ratio, we also subsample our training data to cap the ham to spam ratio within a certain limit. Co-authored-by: jomapp <17314077+jomapp@users.noreply.github.com> Co-authored-by: das <das@tutao.de> Co-authored-by: abp <abp@tutao.de> Co-authored-by: Kinan <104761667+kibibytium@users.noreply.github.com> Co-authored-by: sug <sug@tutao.de> Co-authored-by: nif <nif@tutao.de> Co-authored-by: map <mpfau@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| lib | ||
| test | ||
| LICENSE.txt | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
tutanota-utils
This is a collection of common utils we use across multiple projects/modules internally. As creating this module really is just an intermediate step towards re-organising some of the dependency structure of our software, it is most likely going to change a lot in the future and might even disappear altogether. For these reasons we strongly discourage anyone outside of our organisation to directly depend on this module.