# Zero Trust for AI Systems: Why Authorization Can’t Live Inside the Model

> Source: <https://www.coalitionforsecureai.org/zero-trust-for-ai-systems-why-authorization-cant-live-inside-the-model/>
> Published: 2026-09-16 17:05:27+00:00

September 2026 CoSAI’s Preparing Defenders for AI workstream (WS2) has released its latest paper, Zero Trust for AI Systems, a guide for applying one of security’s most established design patterns to the newest category of insider threat: the AI system itself. The timing isn’t abstract. Over the summer, several frontier […]

The post [Zero Trust for AI Systems: Why Authorization Can’t Live Inside the Model](https://www.coalitionforsecureai.org/zero-trust-for-ai-systems-why-authorization-cant-live-inside-the-model/) appeared first on [Coalition for Secure AI](https://www.coalitionforsecureai.org).