rebuff

Tech stack & purpose

Rebuff is a self-hardening prompt injection detector designed to protect AI applications from prompt injection attacks through a multi-layered defense system. The project offers four layers of defense: heuristics to filter potentially malicious input, LLM-based detection using a dedicated language model to analyze prompts, a vector database to store and recognize attack embeddings, and canary tokens to detect prompt leakages. Rebuff is built with Python and JavaScript/TypeScript SDKs, uses OpenAI's language models for detection, and integrates with vector databases like Pinecone and Chroma as well as Supabase for data storage; the frontend is built with Next.js and Tailwind CSS.

Community & reference links

• Discord

Languages

Contributors

• Willem Pienaar215 commits
• Shahram Anver63 commits
• Sean Morgan34 commits
• Caleb Herbel12 commits
• Risto McGehee10 commits
• Mehrin Kiani4 commits
• ProtectAI2 commits
• risto-liftoff1 commits
• protectai-sv1 commits
• samya1234561 commits
• Badar Ahmed1 commits
• Shahram1 commits