AWS AI Practitioner
A company built an AI chatbot. The chatbot uses large language models (LLMs) to answer user questions. The company wants to keep the chatbot's LLM instructions private. Which security risk should the company consider?
A
Data poisoning
B
Prompt leakage
✓ Correcta
C
LLM hallucinations
D
Output ungroundedness
Explicación
Prompt leakage is a security risk where the system prompt or instructions given to an LLM are exposed to users through the model's responses. When a company wants to keep its LLM instructions private, prompt leakage is the primary security concern to address.