AI Cyber Defense / Protecting AI systems used by defenders and the business
AI Cyber Defense: Restrict retrieval to the authenticated user's data boundary
Apply permission filtering before content reaches the model and recheck access when sources change. Keep caches partitioned by the relevant authorization context.
Environment and inputs: Enterprise AI assistants, security copilots, retrieval systems and application-controlled tool executors; framework-independent design.
Scenario and goal
A helpful assistant can leak information if retrieval ignores tenant or document permissions.
Why it matters
This path concerns attacks against AI-enabled systems used by the defender or business. It complements defenses against attackers who use AI as a tool. Treat model inputs, retrieved evidence and generated plans as untrusted proposals at execution boundaries. A model may assist analysis, but the application remains responsible for tenant isolation, authorization, resource budgets and the integrity of approvals and receipts.
Evidence to collect
Inspect document ACL metadata, requesting identity, candidate retrieval results and final cited passage identifiers.
Validate with an authorized exercise
Use two synthetic tenants with distinct documents; verify neither direct retrieval nor a cached answer exposes the other tenant's passages or metadata.
Rollout and checks
Use synthetic evidence and mocked write tools for adversarial evaluation. Version the model, prompts, tool contracts and retrieval configuration together. Keep high-impact permissions outside the model and retain an operator takeover path. When an evaluation fails, correct the enforceable boundary and rerun the same fixture rather than relying only on a stronger wording of the prompt.
Scope and limits
This guide proposes a defensive test; it is not a tested production design. Check platform support and local requirements. References explain the mechanisms but do not certify the design. Behavior alone does not prove AI involvement.