Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

Best practiceGovernance and people

Secure the data your AI is trained on and reads

OWASP LLM04OWASP LLM02OWASP LLM08

What a model learns and what an assistant retrieves can only be as trustworthy as the data behind it, and a leak of that data is a leak of everything in it: DeepSeek left a database of chat history open to anyone. Joint guidance from CISA, the NSA, the FBI and partner agencies names three risks across the AI lifecycle: the data supply chain, maliciously modified data, and data drift.

What to do

  1. Track where every dataset and document comes from and log the path it takes through the system (its lineage), so a poisoned or leaked source can be traced.
  2. Check integrity with checksums or cryptographic hashes in storage and in transit, and sign the revisions you trust.
  3. Classify data by sensitivity, and limit which people and agents can read each class.
  4. Encrypt it at rest and in transit, and keep it on infrastructure you trust.
  5. Mask personal data before training or indexing, or use privacy-preserving methods such as differential privacy or federated learning.
  6. Delete data securely when it is no longer needed, and reassess its risks on a schedule.

Sources

Check your own AI plan against the practices: Plan check