Adversarial Attacks in AI-Driven RAN Slicing: SLA Violations and Recovery

TL;DR

This paper investigates how adversarial jamming affects AI-based RAN slicing in 5G networks, causing SLA violations and delayed recovery, highlighting vulnerabilities in current DRL-driven resource allocation.

Contribution

It introduces an analysis of adversarial attacks on AI-driven RAN slicing, demonstrating their impact on SLA violations and recovery dynamics in next-generation networks.

Findings

Adversarial jamming can cause severe SLA violations in RAN slicing.

Budget constraints limit the adversary but still induce significant disruptions.

DRL-based resource allocation recovers only after a notable delay post-attack.

Abstract

Next-generation (NextG) cellular networks are designed to support emerging applications with diverse data rate and latency requirements, such as immersive multimedia services and large-scale Internet of Things deployments. A key enabling mechanism is radio access network (RAN) slicing, which dynamically partitions radio resources into virtual resource blocks to efficiently serve heterogeneous traffic classes, including enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). In this paper, we study the impact of adversarial attacks on AI-driven RAN slicing decisions, where a budget-constrained adversary selectively jams slice transmissions to bias deep reinforcement learning (DRL)-based resource allocation, and quantify the resulting service level agreement (SLA) violations and post-attack recovery behavior. Our results indicate that budget-constrained adversarial jamming can induce severe and slice-dependent steady-state SLA violations. Moreover, the DRL agent's reward converges toward the clean baseline only after a non-negligible recovery period.