AI engineering glossary · Evals guardrails AI security
What is cross-tenant leakage?
Cross-tenant leakage: A failure in a multi-customer system where one customer's data becomes visible to another, for example through shared caches, indexes or fine-tuned models. In AI applications it is prevented by strict per-tenant filtering and isolation.
Cross-tenant leakage: an example
Two firms share one search index, and a query from firm A returns a contract from firm B.
Related terms
More Evals guardrails AI security terms
- Data exfiltration
- Data masking
- Data poisoning
- DeepEval
- Defence in depth
- Denial of wallet
- Direct prompt injection
- Egress filtering
Where you learn it
Cross-tenant leakage is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.