Skip to content

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Securing Agentic AI with OS-Level Intent-Driven Capabilities

It is argued that securing agen-tic AI systems requires rethinking authorization at the operating-system boundary and proposed intent-driven capabilities, a new authorization abstraction that dynamically derives task-specific resource bounds from the user’s prompt and enforces least-privilege access.

Miguel Lourenço, R. Bruno · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.