Sep 2026· IEEE Conference on Communications and Network Security· pp. 1-9· 0 citations· 34 references
Computer Science
TL;DR
This paper proposes a split-control architecture in which an untrusted planner emits typed security intents, a deterministic governor checks each intent against safety, resource, temporal-stability, and proportionality invariants, and only admitted actions are bound to signed receipts and compiled into pre-installed eBPF map updates.
Abstract
Adaptive security at the network edge increasingly relies on automated planners, including rule-based controllers, learned policies, and LLM-assisted agents, that translate observations into enforcement actions. Once such a planner can influence live policy state, syntactic validity is not enough. A semantically wrong action, produced from incomplete or manipulated observations, can be faithfully executed by an enforcement substrate that cannot judge mission context. We address this problem by treating the boundary between planner output and kernel enforcement input as the primary security object. We propose a split-control architecture in which an untrusted planner emits typed security intents, a deterministic governor checks each intent against safety, resource, temporal-stability, and proportionality invariants, and only admitted actions are bound to signed receipts and compiled into pre-installed eBPF map updates. The paper formalizes this trust-boundary problem, defines three threat classes, develops the governor admission predicate, and reports an end-to-end prototype. Across rule-based and LLM-assisted planners on a Raspberry Pi 5 testbed connected to the university’s 5G Test Network, the governor admits, rejects, and bounds intents at microsecond cost without disrupting protected-flow regularity. The contribution is conceptual as much as empirical: adaptive security does not need to trust the author of an action. It needs a mediation boundary that decides whether the action is admissible.
Agentic artificial intelligence can decompose legal objectives, retrieve authorities, invoke external tools, draft documents, communicate with stakeholders, and execute multi-step workflows. In high-risk legal settings, a final approval click is not an adequate control: errors can propagate across a trajectory, evidenc...
Shatrunjay Kumar Singh· International Journal of Inn...· 0 citations
A conditional decision-preservation proposition: successful local admission implies that a specified synchronous policy would authorize the same action at the admission point, provided approval is sound, all policy dependencies are represented and current, observations are faithful, and consumption is atomic.
The results show that MetaPermit produces 31% more consistent authorization decisions than LLM-driven authorization and outperforms the state-of-the-art defenses CaMeL and IPIGuard in both task completion and robustness to IPI attacks, with no malicious tool calls executed.
Han-Zhang Ma, Alicia Y. Hariri, Tian-Xiang Shen et al.· arXiv.org· 0 citations
This work formalizes the admission calculus and the assumptions connecting it to mediated execution, and establishes tested implementation behaviors and local costs, not production failure rates or comparisons of language-model capability.
It is argued that this path from a candidate action to privileged side effects must be governed outside the model, and study an architecture interposing four roles (planner, policy gate, executor, auditor) between agent and operating system.
Two robustness notions are formalized, each mechanism by ablation is validated by ablation, and how often the multi-source precondition holds on sanctions designations and software supply-chain provenance is measured.
Anmol Pandey, A. Jain, Liang-Wei Chen et al.· 0 citations