rebuff - LLM Prompt Injection Detector

[Firefly21 Emerald Member Posts:96 Threads:52 Reputation 0]

Rebuff is designed to protect AI applications from fast injection (PI) attacks through a multi-layered defense.

https://github.com/protectai/rebuff

Features

Rebuff offers 4 layers of defense:

• Heuristics: Filter out potentially malicious input before it reaches the LLM.
  
• LLM-based detection: Use a dedicated LLM to analyze incoming prompts and identify potential attacks.
  
• VectorDB: Store embeddings of previous attacks in a vector database to recognize and prevent similar attacks in the future.
  
• Canary tokens: Add canary tokens to prompts to detect leakages, allowing the framework to store embeddings about the incoming prompt in the vector database and prevent future attacks.