Skip to content
AI Security

Interview question · LLM Application Security

Can a vector search API leak confidential information even when it never returns the documents themselves?

Similarity scores, result counts, snippets and ranking all say something about what is in the index. If authorization is applied after search, the search itself is the leak.

mediumNewPreparation tags: Microsoft, Google, DatabricksUpdated Nov 2026

Similarity scores, result counts, snippets and ranking all say something about what is in the index. If authorization is applied after search, the search itself is the leak.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

The answer works through 6 follow-ups like an interviewer would

A multi-tenant RAG product keeps all tenants' embeddings in one shared vector index with a tenant ID field.

  1. How could one tenant learn about another's data?
  2. What if the tenant filter is applied inside the vector query?
  3. What if scores and counts are returned to clients?
  4. What gives the strongest isolation?
  5. How would you test tenant isolation?
  6. What design would you choose?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackCosine similarity decides what a RAG system retrieves. How would you make retrieval prefer trustworthy sources instead of just similar ones?Next in this trackDesign an ingestion pipeline for a RAG index that resists poisoning, and explain how you would estimate the poisoning risk that remains.Next in this trackArchitect the guardrail pipeline for a customer-facing financial assistant, including how you guard streamed responses.
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.