Trustworthy AI-Driven Dynamic Hybrid RIS: Joint Optimization and Reward Poisoning-Resilient Control in Cognitive MISO Networks

2026-03-27

AI Summary

This work addresses the challenges of unreliable secondary links, energy constraints, and vulnerability to reward poisoning attacks in deep reinforcement learning (DRL) within cognitive MISO networks. To this end, it proposes an energy-aware dynamic hybrid reconfigurable intelligent surface (RIS) capable of real-time switching between passive and active modes, jointly optimizing transmit beamforming and RIS phase shifts. The study presents the first systematic investigation of reward poisoning attacks against DRL agents in RIS-aided cognitive networks and introduces a lightweight, real-time defense mechanism that integrates the soft actor-critic (SAC) algorithm with reward clipping and statistical anomaly filtering, while explicitly modeling hardware impairments and cascaded channels. Experimental results demonstrate that the proposed approach achieves a superior trade-off between throughput and energy efficiency, significantly outperforming existing DRL baselines and effectively preserving secondary user performance under adversarial conditions.

Abstract

Cognitive radio networks (CRNs) are a key mechanism for alleviating spectrum scarcity by enabling secondary users (SUs) to opportunistically access licensed frequency bands without harmful interference to primary users (PUs). To address unreliable direct SU links and energy constraints common in next-generation wireless networks, this work introduces an adaptive, energy-aware hybrid reconfigurable intelligent surface (RIS) for underlay multiple-input single-output (MISO) CRNs. Distinct from prior approaches relying on static RIS architectures, our proposed RIS dynamically alternates between passive and active operation modes in real time according to harvested energy availability. We also model our scenario under practical hardware impairments and cascaded fading channels. We formulate and solve a joint transmit beamforming and RIS phase optimization problem via the soft actor-critic (SAC) deep reinforcement learning (DRL) method, leveraging its robustness in continuous and highly dynamic environments. Notably, we conduct the first systematic study of reward poisoning attacks on DRL agents in RIS-enhanced CRNs, and propose a lightweight, real-time defense based on reward clipping and statistical anomaly filtering. Numerical results demonstrate that the SAC-based approach consistently outperforms established DRL baselines, and that the dynamic hybrid RIS strikes a superior trade-off between throughput and energy consumption compared to fully passive and fully active alternatives. We further show the effectiveness of our defense in maintaining SU performance even under adversarial conditions. Our results advance the practical and secure deployment of RIS-assisted CRNs, and highlight crucial design insights for energy-constrained wireless systems.

Problem

• Reconfigurable Intelligent Surface
• Cognitive Radio Networks
• Reward Poisoning Attack
• Energy Harvesting
• Trustworthy AI

Innovation

• Dynamic Hybrid RIS
• Soft Actor-Critic
• Reward Poisoning Defense
• Cognitive MISO Networks
• Energy-Aware RIS