protectai/rebuff
Self-hardening prompt injection detector that protects AI applications from malicious prompt attacks.
Not currently ranked — collecting fresh signals.
star history
Rebuff is a security framework designed to protect AI applications from prompt injection attacks through multiple defensive layers. It uses heuristics to filter malicious input before it reaches the LLM, employs a dedicated LLM to analyze incoming prompts and identify potential attacks, stores embeddings of previous attacks in a vector database to recognize and prevent similar threats, and uses canary tokens to detect prompt leakages. Available as TypeScript and Python SDKs with self-hosting options.
Frequently asked
- What is protectai/rebuff?
- Self-hardening prompt injection detector that protects AI applications from malicious prompt attacks.
- Is rebuff open source?
- Yes — protectai/rebuff is open source, released under the Apache-2.0 license.
- What language is rebuff written in?
- protectai/rebuff is primarily written in TypeScript.
- How popular is rebuff?
- protectai/rebuff has 1.5k stars on GitHub.
- Where can I find rebuff?
- protectai/rebuff is on GitHub at https://github.com/protectai/rebuff.