# An Inline Control Architecture for Language Models in Intelligent Transportation Systems

arXiv: https://arxiv.org/abs/2608.04065 · HTML: https://mlsanity.com/paper/2608.04065/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 7 of 7)

- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving](https://mlsanity.com/paper/2202.08449/) (2022)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [Prompting Is Programming: A Query Language for Large Language Models](https://mlsanity.com/paper/2212.06094/) (2022)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [KoMA: Knowledge-driven Multi-agent Framework for Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2407.14239/) (2024)
- [A Survey of Security and Privacy Issues in V2X Communication Systems](https://mlsanity.com/paper/2208.14674/) (2022)

## Abstract (arXiv)

Vehicle-to-everything (V2X) systems increasingly incorporate large language models (LLMs) for semantic tasks such as message summarization, operator assistance, and decision support at roadside units and edge nodes. Although these components are not part of safety-critical control loops, they introduce prompt-level attack surfaces that are not addressed by traditional V2X security mechanisms focused on authentication and message integrity. This paper presents Guarded-V2X, an inline semantic guardrail architecture for securing LLM-enabled V2X services under real-time constraints. The proposed system integrates rule-based ingress filtering, a lightweight safety classifier, policy-constrained structured generation, trusted-only retrieval, and post-decision adjudication to enforce machine-checkable safety boundaries prior to downstream execution. Guarded-V2X is evaluated using a four-stage experimental pipeline encompassing intrusion vulnerability analysis, calibration and latency benchmarking, guardrail validation, and robustness under adversarial stress. Experiments are conducted on a V2X-aligned simulated dataset derived from RSU advisories, operator messages, and annotated V2X message summaries. Results show that unguarded and prompt-only baselines retain residual vulnerability under multi-turn adversarial trials, while Guarded-V2X consistently reduces intrusion acceptance success rates and eliminates observed unsafe completions in two-turn settings, without exceeding latency budgets for V2X semantic advisory paths.