Skip to content

Safetorun/LLMSecurityFramework

Repository files navigation

The 4 step process

  1. Describe the architecture of your application - include where user (or attacker) input comes in, where it is rendered, any storage used by the LLM (e.g. for RAG), training data, fine-tuning data, ‘memory’ or caching mechanisms and any external data sources
  2. Walk through the flow-chart to understand risk factors, outputs and attack vectors - add them to your diagram as you go
  3. Add each ‘risk’ to your diagram and understand the applicability of each one
  4. Apply your defences to ensure you are mitigating all risks

{% @mailchimp/mailchimpSubscribe %}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors