Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents
Fine-tuned RoBERTa-large task permission classifier matches Claude Haiku 4.5 on access scoping for AI agents, cutting severity-weighted attack surface by 84.4%.
The paper evaluates a three-source task-based permission architecture for AI agents combining role-based permission ceilings, a task permission classifier, and policy-based prohibitions. A fine-tuned RoBERTa-large security gate matched few-shot Claude Haiku 4.5 on a 600-prompt dataset, with macro-F1 0.881 versus 0.886, precision 0.897 versus 0.842, and lower severity-weighted residual risk (0.63 versus 1.12). An attack-surface elimination metric shows the role ceiling alone closes 27.9% of the severity-weighted surface while adding the task classifier closes 84.4%. The work establishes task-granular access control as a measured, deployable mechanism for reducing attack surface in agentic deployments.
- Task-granular access control eliminates standing credential exposure for AI agents
- RoBERTa-large gate matches Claude Haiku 4.5 with macro-F1 0.881
- Role ceiling closes 27.9% of severity-weighted attack surface
- Task classifier raises closed surface to 84.4%
- Trusted supervisor component does not need to scale with the agent
From the original article
1 min read at arxiv.orgAI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes all permissions the employee role might ever need. Role-based access control made this compromise for human principals because scoping access per task was infeasible.
By Halil Burak Noyan · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.