Supply Chain Security for Models

The AI Supply Chain

ComponentSourceRisk
Pre-trained modelModel hub (Hugging Face), vendor APIBackdoor, pickle exploit, license issues
Fine-tuning dataInternal data, public datasets, contractorsPoisoning, PII, quality issues
Model serving frameworkPyTorch, vLLM, TGI, OllamaVulnerabilities in inference code
Plugins/toolsFirst-party, third-party, communityMalicious tool, data exfiltration
Vector databasePinecone, Weaviate, ChromaDB, pgvectorPoisoned embeddings, unauthorized access
Python dependenciesPyPI packagesDependency confusion, typosquatting

Controls

Model Artifact Security

  • Only download from verified sources
  • Verify hash against published checksums
  • Use safetensors format to prevent pickle execution
  • Scan model files with model-specific security tools
  • Document model provenance: source, version, modification history

Dependency Management

  • Pin all dependency versions
  • Use lockfiles (pip-compile, poetry.lock)
  • Scan dependencies for known vulnerabilities (Snyk, pip-audit)
  • Use private PyPI mirror for production dependencies
  • Review new dependency additions before approval

Tool and Plugin Security

  • Vet all third-party tools before enabling
  • Sandbox tool execution environments
  • Audit tool permissions (what data can the tool access?)
  • Monitor tool call patterns for anomalies
  • Maintain an approved tool registry

SBOM for AI

Create an AI-specific Software Bill of Materials that includes:

□ Base model name, version, source, hash
□ Fine-tuning dataset source and version
□ Model serving framework and version
□ All Python dependencies with versions
□ System prompt version and change history
□ Tool/plugin list with versions
□ RAG data sources and update schedule
□ Vector database engine and version