Skip to content
Search
tool2023ReviewedOpen access

Rebuff: Self-Hardening Prompt Injection Detector

Protect AI

GitHub

View resource

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

Input FilteringPrompt Injection
#tool#detection#canary-tokens#open-source

Framework mappings

OWASP Top 10 for LLM Applications
  • LLM01Prompt Injection

Cite

@misc{protect2023rebuff,
  title = {{Rebuff: Self-Hardening Prompt Injection Detector}},
  author = {{Protect AI}},
  year = {2023},
  url = {https://github.com/protectai/rebuff}
}