AI engineering glossary · Evals guardrails AI security
What is STRIDE threat model?
STRIDE threat model: A mnemonic for six categories of security threat: Spoofing, Tampering, Repudiation, Information disclosure, Denial of service and Elevation of privilege. It is used in threat modelling to prompt systematic questions about each part of a design, including AI pipelines.
STRIDE threat model: an example
For a chatbot API, a reviewer asks how information disclosure could occur and finds that logs store raw customer prompts.
Related terms
More Evals guardrails AI security terms
- Structured output validation
- SWE-bench
- Synthetic test data
- System prompt extraction
- Threat modelling
- Tool poisoning
- Tool-call accuracy
- Topical rails
Where you learn it
STRIDE threat model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.