Skip to content

Mitigate adversial attacks on LLMs via automatic deployment of predefined plugins.

Notifications You must be signed in to change notification settings

cisco-open/AdversaryShield

Repository files navigation

AdversaryShield

This project is being developed as a solution to mitigate adversial attacks on LLMs via automatic deployment of predefined plugins.

Description

AdversaryShield project is composed of three main services:

  • Tabularium provides the administrator with an interface to CRUD plugins and store into the DB;
  • Galea creates the containers to run the plugins based on manager configuration and helm charts;

Other services used are:

  • <Database>: Used to store user test suites.

Service Diagram

Diagram

Getting started

Dependencies

  • Docker Engine (Docker Desktop)
  • minikube
  • Python

Deploying

ToDo: Run the launch.sh script.

Usage

Launch the application and use the Strategos provided interface to store the plugins (and their parameters) via the plugins view. WIP: The run view will provide the user with the posibility of running a prompt through the plugins towards the desired LLM and have the outputs filtered in case of adversial attacks. Outputs with respective inputs will be tracked within the database for later review of mitigations.

Authors

Version history

  • alpha 0.1
    • Init

License

Work in progress.

About

Mitigate adversial attacks on LLMs via automatic deployment of predefined plugins.

Resources

Code of conduct

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published