AI Posture Check Take the Check
LLM04 · OWASP LLM Top 10

Data and Model Poisoning (LLM04)

An attacker injects malicious data into training, fine-tuning, or RAG-corpus content to alter model behavior in their favor — often subtly, often persistently.

Examples

  • Poisoning a public web corpus that the target model later trains on.
  • Inserting backdoor-trigger content into a fine-tuning dataset.
  • Poisoning a RAG corpus with content designed to bias outputs on specific queries.

Recommended controls

  • Provenance tracking for training data
  • Adversarial testing for backdoors
  • RAG corpus content review
  • Anomaly detection on training-data ingest

Posture Check checkpoint

Posture Check questions Q16–Q20. Score affects Model dimension.

Score yourself against this framework.

The AI Posture Check is a free 30-question self-assessment that maps your gaps directly to OWASP LLM Top 10, NIST AI RMF, and ISO 42001.

Take the AI Posture Check
Need help operationalizing this?

Talk to a CWS engineer about your AI security program.

Schedule a Discovery Call to scope a Standard Audit or Enterprise Program.

Schedule a Discovery Call