# When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control System

arXiv: https://arxiv.org/abs/2605.20037 · HTML: https://mlsanity.com/paper/2605.20037/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 19 May 2026.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 22 of 22)

- [Reinforcement learning](https://mlsanity.com/paper/2405.10369/) (2024)
- [A Survey on Model-based, Heuristic, and Machine Learning Optimization Approaches in RIS-aided Wireless Networks](https://mlsanity.com/paper/2303.14320/) (2023)
- [Communication and Computation O-RAN Resource Slicing for URLLC Services Using Deep Reinforcement Learning](https://mlsanity.com/paper/2202.06439/) (2022)
- [Dynamic SDN-based Radio Access Network Slicing with Deep Reinforcement Learning for URLLC and eMBB Services](https://mlsanity.com/paper/2202.06435/) (2022)
- [Federated Deep Reinforcement Learning for Open RAN Slicing in 6G Networks](https://mlsanity.com/paper/2206.11328/) (2022)
- [Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning](https://mlsanity.com/paper/2205.14842/) (2022)
- [Network Slicing with MEC and Deep Reinforcement Learning for the Internet of Vehicles](https://mlsanity.com/paper/2201.11295/) (2022)
- [A Deep Reinforcement Learning Approach for Service Migration in MEC-enabled Vehicular Networks](https://mlsanity.com/paper/2201.11831/) (2022)
- [Hybrid Hierarchical DRL Enabled Resource Allocation for Secure Transmission in Multi-IRS-Assisted Sensing-Enhanced Spectrum Sharing Networks](https://mlsanity.com/paper/2312.01071/) (2023)
- [Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning](https://mlsanity.com/paper/2305.10681/) (2023)
- [Performance Optimization of Energy-Harvesting Underlay Cognitive Radio Networks Using Reinforcement Learning](https://mlsanity.com/paper/2505.14581/) (2025)
- [Federated Learning-based MARL for Strengthening Physical-Layer Security in B5G Networks](https://mlsanity.com/paper/2507.06997/) (2025)
- [Mean-Field Game and Reinforcement Learning MEC Resource Provisioning for SFC](https://mlsanity.com/paper/2201.11830/) (2022)
- [Deep Deterministic Policy Gradient to Minimize the Age of Information in Cellular V2X Communications](https://mlsanity.com/paper/2210.09586/) (2022)
- [Optimizing Cognitive Networks: Reinforcement Learning Meets Energy Harvesting Over Cascaded Channels](https://mlsanity.com/paper/2507.06981/) (2025)
- [ML-Enabled Open RAN: A Comprehensive Survey of Architectures, Challenges, and Opportunities](https://mlsanity.com/paper/2604.01239/) (2026)
- [Reconfigurable Intelligent Surface for Physical Layer Security in 6G-IoT: Designs, Issues, and Advances](https://mlsanity.com/paper/2311.08112/) (2023)
- [Maximizing Reliability in Overlay Radio Networks with Time Switching and Power Splitting Energy Harvesting](https://mlsanity.com/paper/2507.06983/) (2025)
- [Overview of RIS-Enabled Secure Transmission in 6G Wireless Networks](https://mlsanity.com/paper/2312.02728/) (2023)
- [Trustworthy AI-Driven Dynamic Hybrid RIS: Joint Optimization and Reward Poisoning-Resilient Control in Cognitive MISO Networks](https://mlsanity.com/paper/2604.01238/) (2026)
- [Competitive Algorithms and Reinforcement Learning for NOMA in IoT Networks](https://mlsanity.com/paper/2201.12395/) (2022)
- [Joint Hybrid Transceiver and Reflection Matrix Design for RIS-Aided mmWave MIMO Cognitive Radio Systems](https://mlsanity.com/paper/2406.08797/) (2024)

## Abstract (arXiv)

Reward-poisoning attacks present a significant risk to learning-based wireless control systems. Given this, we propose a Disagreement-Guided Reward Poisoning (DGRP) adaptive attack on a Soft Actor-Critic (SAC) agent. In a Cognitive Radio Network (CRN) environment assisted by Reconfigurable Intelligent Surfaces (RIS), the SAC agent is tasked with maximizing the long-term secondary users' (SUs) rate by simultaneously optimizing the transmission power of the SU transmitter and the RIS phase shifts. DGRP corrupts rewards, particularly when the SAC dual critics exhibit substantial disagreement-especially in high-leverage, high-uncertainty states-resulting in distorted value estimations and guiding the policy towards suboptimal actions. Our findings demonstrate that DGRP substantially diminishes the performance improvements typically provided by RIS and degrades transmission quality. We further investigate key attack parameters and determine their impact on learning. In comparison to periodic-timing and exploration-triggered baselines, DGRP consistently causes greater damage, highlighting the necessity of considering disagreement-aware threats when evaluating the robustness of Deep Reinforcement Learning (DRL) in RIS-assisted networks.