14Can prompt caching or response caching in an LLM application leak data between users?▼mediumNewOpenAIAnthropicGoogle◆ premiumCaches are shared state, and shared state crosses tenants. The scored answer separates response caches from prompt prefix caches and keys each so one user can never read or detect another's data.Open full answer →
27Can a vector search API leak confidential information even when it never returns the documents themselves?▼mediumNewMicrosoftGoogleDatabricks◆ premiumSimilarity 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.Open full answer →