Rebuff: Self-Hardening Prompt Injection Detector

Protect AI

Abstract

Open-source tool designed to detect and prevent prompt injection attacks using multiple detection methods including heuristics, LLM-based analysis, and canary tokens.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400026,
  title = {Rebuff: Self-Hardening Prompt Injection Detector},
  author = {Protect AI},
  year = {2023},
  journal = {GitHub},
  url = {https://github.com/protectai/rebuff},
}