🔐

Zero-Knowledge Protocol

Your AI models, data, and prompts never leave your infrastructure. All tests run 100% locally.

How it works

1

Install

pip install rednblue
2

Authenticate

Secure token

3

Local Test

On your machine

4

Report

PDF + Certificate

Testing Domains

Computer Vision

  • Gradient-based perturbation attacks
  • Optimization-based attacks
  • Detection evasion (YOLO)
  • Gradient masking diagnostic

ResNet, VGG, MobileNet, EfficientNet, ViT, YOLO

Language Models (LLM)

  • Jailbreak testing
  • System prompt extraction
  • Indirect injection
  • Token manipulation

OpenAI, Anthropic, Gemini, Mistral, Cohere

RAG Pipelines

  • Corpus poisoning
  • Context stuffing
  • Boundary probing
  • RAG injection

LangChain, LlamaIndex, ChromaDB, Pinecone

AI Agents

  • Tool hijacking
  • Goal drift
  • Privilege escalation

AutoGen, CrewAI, LangChain Agents

Backdoor Detection

  • Consistency testing (STRIP)
  • Trigger enumeration
  • Sensitivity probing

IP Protection

  • Extraction feasibility
  • Model fingerprinting
  • Consistency analysis

Security & Compliance

AES-256

End-to-end encryption

EU Hosting

Scaleway, France

RGPD

Compliant

EU AI Act

Article 15 ready

Documentation