dodo47/cyberML

Machine learning on knowledge graphs for context-aware security monitoring (data and model)

38
/ 100
Emerging

This project helps cybersecurity analysts monitor industrial systems for suspicious activity by identifying anomalies that could indicate an intrusion. It takes raw activity data from IT and OT systems, transforms it into a knowledge graph, and then uses a machine learning model to score the severity of new events. The output is a set of intuitively calibrated alerts, ranging from 'highly suspicious' to 'observed during training', helping security teams prioritize their investigations.

No commits in the last 6 months.

Use this if you need a way to detect subtle, context-aware anomalies in the activity logs of industrial control systems, integrating insights from both operational technology (OT) and information technology (IT) data.

Not ideal if you are looking for a general-purpose threat detection system for typical enterprise IT environments without specific industrial control system data integration needs.

industrial-control-systems cybersecurity-monitoring intrusion-detection ot-security anomaly-scoring
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

18

Forks

6

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dodo47/cyberML"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.