QuestionQ58

VerifiedSecuring AI systems

An airline corporation wants to implement a chatbot application using a large language model (LLM) so that its customers can:

  • Ask questions and receive answers about flight details.
  • Have the option to upload files.

Which of the following security controls should the airline use to protect against malicious input and unauthorized use beyond the service-level agreement?

Choose two
Explanation

Prompt guardrails constrain and sanitize user-supplied prompts and uploaded content to block malicious or adversarial input to the LLM, while model token quotas enforce usage limits so that no user or session can consume resources beyond what the service-level agreement allows; role-based access control and network firewall rules address identity and network-layer concerns rather than LLM-specific input handling and consumption abuse.

Community Discussion

No comments yet. Be the first to start the discussion!