← All tags · All resources · All guides

#defense-in-depth

1 resource and 1 guide tagged #defense-in-depth on ChangeGamer.

• AI Control for Agents: The Insider-Threat Defense Model · Guide
  What "AI control" means as a security paradigm distinct from alignment: Google DeepMind's Detection (D1-D4) and Prevention/Response (R1-R3) tiers for treating a deployed agent's own actions, not just its inputs, as the threat to defend against.

Guides

• How to Defend an AI Agent Against Prompt Injection · guide
  A decision framework for matching Action-Selector, Plan-Then-Execute, Dual LLM, and the other named architectural patterns to a task's actual blast radius, including when to compose two patterns together and when none of them is worth the overhead.