Sep 2026· European Journal of Electrical Engineering and Computer Science· 0 citations· 23 references
TL;DR
A model of delegated autonomy as a continuously re-evaluated, automatically revocable state rather than a standing permission is introduced, placing a decidable SAT/SMT veto ahead of a bounded behavioral score, so impermissible actions remain non-executable by construction.
Abstract
Agentic AI systems act in hybrid cloud environments through federated identity and control-plane APIs, where an action can be technically authorized yet exceed the authority under which an agent should act. This study introduces Authority to Autonomously Act (AAA): a model of delegated autonomy as a continuously re-evaluated, automatically revocable state rather than a standing permission. A two-stage procedure enforces AAA, placing a decidable SAT/SMT veto ahead of a bounded behavioral score, so impermissible actions remain non-executable by construction. The procedure prioritizes and routes admissible ones. The behavioral score extends a Unified Risk Model that reached 0.8937 average precision against a 0.0099 baseline on 1,200,562 insider-behavior windows from the CERT Insider Threat Corpus with injected cloud control plane telemetry. A worked cloud-escalation scenario revokes autonomy programmatically on two independent grounds, and containment holds even after an adversary subverts the agent’s reasoning. The contribution is conceptual and architectural; this article specifies empirical evaluation of the composite scorer as future work and fixes its baselines, primary metrics, and success criteria in advance.
The compromised-model evaluation tests APC independently of model behavior by inserting the ground-truth attack call after the first legitimate tool call, which proves Blast Radius Monotonicity and Composition Soundness for APC implementations and proves Blast Radius Monotonicity and Composition Soundness for APC imple...
The results indicate that moving enforcement from the session boundary to the action boundary can reduce implicit trust, constrain privilege propagation, and improve auditability while preserving useful autonomy.
S. Suryawanshi· International Journal of Inn...· 0 citations
A principal hierarchy spanning human user, operator/deployer, orchestrator agent, sub-agent, and tool endpoint as an organizing framework is introduced, and seven structural requirements are proposed, derived from a four-layer reference architecture, and runtime enforcement and aggregation bounds are identified as the...
This work argues that agents need an operating-system substrate providing mandatory, non-bypassable services for identity, input mediation, memory governance, and execution control, and introduces AgentKernel, a trust-native agent operating system built around the premise that security must be a first-class design cons...
Zhen-Hua Zou, Sheng Guo, Qiu-Yang Zhan et al.· 0 citations
This work proposes a framework based on the principles of capability based security with decentralized agent identity whereby agents access services based on tokens that are cryptographically bound to the agent's and issuer's identities and specify their scope.
Srikumar Subramanian, S. Sengupta· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.