๐Ÿ”ฌ
Vigil: Documentation
GitHub Repo
  • ๐Ÿ›ก๏ธVigil
  • Overview
    • ๐Ÿ—๏ธRelease Blog
    • ๐Ÿ› ๏ธInstall Vigil
      • ๐Ÿ”ฅInstall PyTorch (optional)
    • ๐ŸงชUse Vigil
      • โš™๏ธConfiguration
        • ๐Ÿ”„Auto-updating vector database
      • ๐Ÿ—„๏ธLoad Datasets
      • ๐ŸŒWeb server
        • ๐ŸคAPI Endpoints
        • ๐ŸชWeb UI playground
      • ๐ŸPython library
      • ๐ŸŽฏScanners
        • ๐Ÿค—Transformer
        • โ•YARA / Heuristics
        • ๐Ÿ“‘Prompt-response Similarity
        • ๐Ÿ’พVector database
        • ๐ŸคCanary Tokens
    • ๐Ÿ›ก๏ธCustomize Detections
      • ๐ŸŒŸAdd custom YARA signatures
      • ๐Ÿ”ขAdd embeddings
      • ๐ŸCustom scanners
    • ๐Ÿช„Sample scan results
Powered by GitBook
On this page
  1. Overview
  2. Use Vigil
  3. Scanners

Vector database

PreviousPrompt-response SimilarityNextCanary Tokens

Last updated 1 year ago

The vectordb scanner uses a loaded with embeddings of known injection and jailbreak techniques and compares the submitted prompt via similarity search. If the prompt matches within a defined threshold, it will be flagged as potential prompt injection.

This scanner uses ChromaDB with cosine distance as the back-end database. A lower distance score indicates higher similarity.

All embeddings are available on HuggingFace and listed in the section.

๐Ÿงช
๐ŸŽฏ
๐Ÿ’พ
vector database
Datasets