Problem
Research questions and friction points this paper is trying to address.
Adversarial Attacks
RAN Slicing
SLA Violations
AI-driven Resource Allocation
Recovery Behavior
Adversarial Attacks in AI-Driven RAN Slicing: SLA Violations and Recovery
🤖 AI Summary
This study investigates the impact of adversarial attacks on deep reinforcement learning (DRL)-based resource allocation in wireless radio access network (RAN) slicing, with a focus on service-level agreement (SLA) violations. It proposes an analytical framework that integrates adversarial perturbation modeling with SLA performance evaluation to address the threat posed by budget-constrained adversaries who selectively interfere with DRL decisions. The work presents the first systematic quantification of steady-state SLA violation severity and system recovery latency under such attacks, revealing heterogeneous vulnerability across different slice types. Experimental results demonstrate that even limited-budget adversarial interference can induce significant, slice-type-dependent SLA breaches, and that DRL-based systems require a non-negligible recovery period to restore normal performance levels.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
adversarial attacks
AI-driven RAN slicing
deep reinforcement learning
SLA violations
network slicing security
🔎 Similar Papers
No similar papers found.
