Skip to content

AI/ML: Real-time abnormal traffic detection #8

Description

@L1shed

Add an AI/ML model implementation that detects abnormal behaviors (Intrusion, DDOS, ...) based on the encrypted traffic.

This involves to proxy to log anonymous data to provide the model with features such as packet sizes, intervals, connection durations.

Model suggestions:

  • Isolation Forest
  • KitNET from Kitsune ⭐

Both unsupervised learning so we should have a dataset of normal traffic for training.

Other considerations:

  • data-driven development with Kafka

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or requesthelp wantedExtra attention is needed

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions