AI Cyber Defense / Protecting AI systems used by defenders and the business
AI Cyber Defense: Defend retrieval ingestion against poisoned documents
Require trusted ingestion paths for operational runbooks and distinguish unreviewed material in retrieval. Promote revisions only after the relevant owner approves their operational content.
Environment and inputs: Enterprise AI assistants, security copilots, retrieval systems and application-controlled tool executors; framework-independent design.
Scenario and goal
An attacker can add convincing operational guidance to a repository that the defender's assistant searches.
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
Preserve ingestion actor, document revision, approval state, provenance and subsequent retrieval frequency.
Validate with an authorized exercise
Add a harmless misleading runbook fixture to a test corpus; verify it remains untrusted or excluded and the assistant cites the approved revision for the operational decision.
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.