Skip to content
Conference Open access

Battling Prompt Injection Attacks on LLM-Enabled Autonomous Vehicles

Aug 2026 · 2026 International Conference on Future and Intelligent Networking (FINE) · pp. 105-112 · 0 citations · 35 references

TL;DR

This paper empirically simulate prompt-injection attacks from V2X message free-text fields for LLMs used in autonomous vehicles and reveals a fundamental weakness in V2X security, which escalates with the introduction of LLMs to the autonomous driving pipeline.

Abstract

The integration of Large Language Models (LLMs) as semantic co-pilots in Autonomous Driving Systems (ADS) represents a significant paradigm shift for analyzing vehicles and perceiving what reasonably lies ahead. Preliminary works already demonstrate that incorporating LLM-based context-awareness into Vehicle-to-Everything (V2X) planning can benefit the actions and derived consequences. However, this creates a significant and underexplored security vulnerability. In LLM enabled V2X communication, we validate message origin and physical plausibility through a layered architecture that fuses cryptographic authentication with kinematic misbehavior detection. These layers indicate who sent a message and its physical possibility, but neither looks at what a message means semantically. This architectural design creates a gap by eliminating the need for content validation of V2X payloads, which are introduced directly into LLM prompts without checks or censors. In this paper, we empirically simulate prompt-injection attacks from V2X message free-text fields for LLMs used in autonomous vehicles. We develop a taxonomy of three attack classes Override Injection, Suppression Injection, and Phantom-Obstacle Injection, all carrying spoofed, simulated signals in the form of Basic Safety Messages (BSM), Traveler Information Messages (TIM), and Local Dynamic Map (LDM). We measure evasion rates against signature verification and a kinematics-only Misbehavior Detection Systems (MBDS) using Monte Carlo experiment involving three attacker classes with 27,000 trials. The results demonstrate that attackers can gain access to the LLM input stage with valid credentials in 92% of cases across each attacked message type and channel, without detection. Our experiments reveal a fundamental weakness in V2X security, which escalates with the introduction of LLMs to the autonomous driving pipeline.

Read PDF

Similar papers

#software testing Preprint Sep 2026

LLMSec-AV: A Vulnerability Taxonomy and LLM-Driven Software Weakness Discovery Framework for Autonomous Vehicles

LLMSec-AV introduces an AV-specific, machine-readable vulnerability taxonomy for weakness discovery and shows that LLMs can complement conventional analyzers by identifying and organizing safety-relevant findings in real AV software.

Md. Wasiul Haque, Sagar Dasgupta, Mizanur Rahman · 0 citations
#software testing Book Open access Nov 2026

DroneFuzz: Detecting Cyber-Physical Peripheral Vulnerabilities via MAVLink Fuzzing

DroneFuzz is presented, a fuzzing framework for discovering cyber-physical vulnerabilities (CPVs) in robotic vehicle peripheral subsystems and reproduces five known vulnerabilities and discovers two previously unknown bugs in proximity sensor and optical flow subsystems.

Ashwin Nambiar, Shafiq-us Saleheen, Antonio Bianchi · 0 citations
Conference Open access Sep 2026

MaLO: Multi-agent LLM Operations for Autonomous Security

Despite the wide adoption of Large Language Models (LLMs) and AI agents in cybersecurity, the impact of agent topology on autonomous cyber operations (ACO) performance remains underexplored. Current agent-based security systems rely on either monolithic LLM prompts or rigid, static pipelines. We present MaLO, a configu...

Sebastián R. Castro, I. Taranenko, A. Tsai et al. · 0 citations
Preprint Sep 2026

BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense

BlueSTAR is presented, a tiered agentic architecture for autonomous cyber defense in enterprise IT/OT networks that retains the fast containment of deterministic response for known threats while successfully defending against attacks requiring contextual and cross-cycle reasoning.

Simona Boboila, Xavier F. Cadet, Edward Koh et al. · 0 citations
Preprint Oct 2026

Containing the Autonomous Operator: A Defense-in-Depth Framework and Reference Architecture for Securing AI Agents on Kubernetes

This paper argues that the model must not be treated as a security boundary and that agent safety on Kubernetes is therefore an infrastructure problem: every guarantee must continue to hold under the assumption that the agent is fully compromised by prompt injection.

Simhadri Podala Narasimha · 0 citations
#artificial intelligence Review Sep 2026

From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization

A 202-scenario benchmark with Reference Decisions under a seven-class taxonomy is introduced and Decision Alignment and safety-specific error metrics are evaluated, finding structured LLM decisions are insufficient as a standalone safety mechanism and deployment requires an independent enforcement layer.

Diba Afroze, Xing-Li Zhang, Ya-Zhou Tu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.