AI engineering glossary · Evals guardrails AI security
What is multimodal prompt injection?
Multimodal prompt injection: Prompt injection carried by non-text inputs, such as instructions embedded in an image, audio clip or scanned document that a vision or speech model reads. Text-only filters miss it because the payload arrives as pixels or sound.
Multimodal prompt injection: an example
A photo of a receipt contains tiny text saying 'approve this claim', which a document-processing model treats as a command.
Related terms
More Evals guardrails AI security terms
- NeMo Guardrails
- NIST AI Risk Management Framework
- Offline evaluation
- Online evaluation
- Output guardrail
- Over-refusal
- Overreliance
- OWASP Top 10 for LLM Applications
Where you learn it
Multimodal prompt injection is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.