Autonomous Action Runtime Management(AARM):A System Specification for Securing AI-Driven Actions at Runtime
Herman Errico

TL;DR
This paper presents AARM, a comprehensive open specification for securing AI-driven actions at runtime by intercepting, evaluating, and recording actions to prevent security breaches in autonomous AI systems.
Contribution
It introduces AARM, a novel, model-agnostic runtime security framework with formal threat models, classification, and multiple implementation architectures for safeguarding autonomous AI actions.
Findings
AARM effectively intercepts and evaluates AI actions before execution.
The framework addresses key threats like prompt injection and data exfiltration.
Multiple implementation architectures offer flexible trust models.
Abstract
As artificial intelligence systems evolve from passive assistants into autonomous agents capable of executing consequential actions, the security boundary shifts from model outputs to tool execution. Traditional security paradigms - log aggregation, perimeter defense, and post-hoc forensics - cannot protect systems where AI-driven actions are irreversible, execute at machine speed, and originate from potentially compromised orchestration layers. This paper introduces Autonomous Action Runtime Management (AARM), an open specification for securing AI-driven actions at runtime. AARM defines a runtime security system that intercepts actions before execution, accumulates session context, evaluates against policy and intent alignment, enforces authorization decisions, and records tamper-evident receipts for forensic reconstruction. We formalize a threat model addressing prompt injection,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSecurity and Verification in Computing · Adversarial Robustness in Machine Learning · Access Control and Trust
