Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Ingress #129

Open
wants to merge 157 commits into
base: master
Choose a base branch
from
Open

Ingress #129

wants to merge 157 commits into from

Conversation

mazhurin
Copy link
Collaborator

No description provided.

mazhurin and others added 30 commits June 4, 2020 18:34
Unit tests and linting fixes.
… configuration istead of full python model names.
…e.training.model refers to the full module path of the Model class(not the Enum key).
Country and Host features. Stratified sampling(parameter 'max_samples_per_host'). Support for nested features in JSON parser(geoip feature fix).
* DB reader
* SQL based incident detector
* Attack detection and chunks removed from AttackDetection task.
* Incident detector added.
* Incident Labeler class. Tested in Jupyter notebook.
* Optional scaling in AnomalyModel
* Some fixes in Jupyter notebooks.
start in whitelist urls
fix in sending to kafka
* Debug log line removed from AttackDetection

* Organization creating is optional. No classifier in labeler.
* Classifier model. 'classifier_score' column. DBReader fix.

* Classifier pipeline. Incident loader class. Train classifier task.
* Incident detector. Fix for delayed stop.

* Unit tests are working now.

* Linting fixes.
…aly score rather than on both anomaly and classifier score. The reason is that classifier is biased towards historical incidents and is not good in detecting previously unseen patterns. (#113)
* KSQL added to the k8s deployment.
* ed_retrivier removed
parsing weblog in spark
* postprocessing streamin to s3. Tested.
* Readme update. NA fix in postprocessing
* new json weblogs format
* Lostash deployment. LoadBalancer in Kafka.
* Logstash, prediction_behave column, timescaledb.
* Elastic search added to the deployment.
* Host as a key in send_challenge. First testing version of utm_source, utm_medium, utm_capmpaign cstats columns.

* Kafka field names fixes.
* Whitelisting solved challenge IPs

* 20m stats topic size increase. 80GB kafka storage increase.

* domain whitelisting fix

* Grace period for fresh sessions. Warmup period for sessions.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants