Defending Against Network Attacks for Secure AI Agent Migration in Vehicular Metaverses

TL;DR

This paper tackles secure online migration of AI agents in vehicular metaverses under DDoS and malicious RSU threats. It models pre-migration decisions as a POMDP and trains MAPPO agents to minimize total migration latency while resisting attacks. A trust assessment mechanism with adaptive thresholds identifies and bans malicious RSUs to protect data integrity. Numerical results show a latency reduction of about 43.3% and improved defense across direct, indirect, and hybrid DDoS scenarios.

Abstract

Vehicular metaverses, blending traditional vehicular networks with metaverse technology, are expected to revolutionize fields such as autonomous driving. As virtual intelligent assistants in vehicular metaverses, Artificial Intelligence (AI) agents powered by large language models can create immersive 3D virtual spaces for passengers to enjoy on-broad vehicular applications and services. To provide users with seamless and engaging virtual interactions, resource-limited vehicles offload AI agents to RoadSide Units (RSUs) with adequate communication and computational capabilities. Due to the mobility of vehicles and the limited coverage of RSUs, AI agents need to migrate from one RSU to another RSU. However, potential network attacks pose significant challenges to ensuring reliable and efficient AI agent migration. In this paper, we first explore specific network attacks including traffic-based attacks (i.e., DDoS attacks) and infrastructure-based attacks (i.e., malicious RSU attacks). Then, we model the AI agent migration process as a Partially Observable Markov Decision Process (POMDP) and apply multi-agent proximal policy optimization algorithms to mitigate DDoS attacks. In addition, we propose a trust assessment mechanism to counter malicious RSU attacks. Numerical results validate that the proposed solutions effectively defend against these network attacks and reduce the total latency of AI agent migration by approximately 43.3%.

Figures (8)

• Figure 1: Online AI agent migration framework in vehicular metaverses. We systematically present four typical network attacks and their characteristics during AI agent migration.
• Figure 2: The architecture of the proposed MAPPO-based online AI agent pre-migration algorithm and the trust assessment mechanism.
• Figure 3: Average test rewards of MAPPO and other baseline algorithms.
• Figure 4: Average total migration latency under MAPPO and other baseline algorithms.
• Figure 5: Average total migration latency under different sizes of AI agent migration tasks.