rebuff v0.1.0

Rebuff.ai

Self-hardening prompt injection detector

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

Playground • Discord • Features • Installation • Getting started • Docs

Disclaimer

Rebuff is still a prototype and cannot provide 100% protection against prompt injection attacks!

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.

Roadmap

• Prompt Injection Detection
• Canary Word Leak Detection
• Attack Signature Learning
• JavaScript/TypeScript SDK
• Python SDK to have parity with TS SDK
• Local-only mode
• User Defined Detection Strategies
• Heuristics for adversarial suffixes

Installation

npm i rebuff

Getting started

Importing the Rebuff SDK:

import { RebuffSdk } from "rebuff";

Importing the Rebuff API interface:

import { RebuffApi } from "rebuff";

🚧🚧🚧 More Coming Soon 🚧🚧🚧