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

• URL: http://arxiv.org/abs/2605.20037v1
• Date: Tue, 19 May 2026 15:59:43 GMT
• Title: When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control System
• Abstract summary: We propose a Disagreement-Guided Reward Poisoning adaptive attack on a Soft Actor-Critic (SAC) agent.<n>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.<n>DGRP corrupts rewards, particularly when the SAC dual critics exhibit substantial disagreement.
• Score: 7.546882801190319
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability [79.08785366532287]
  We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability.<n>We evaluate the approach in two safety-critical partially observable domains: automated glucose regulation and safety-constrained navigation.
  arXiv  Detail & Related papers  (2026-05-14T01:23:09Z)
• Trustworthy AI-Driven Dynamic Hybrid RIS: Joint Optimization and Reward Poisoning-Resilient Control in Cognitive MISO Networks [7.546882801190319]
  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)<n>This work introduces an adaptive, energy-aware hybrid reconfigurable intelligent surface (RIS) for underlay multiple-input single-output (MISO) CRNs.
  arXiv  Detail & Related papers  (2026-03-27T22:21:33Z)
• Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems [14.028345839891855]
  Retrieval-augmented generation (RAG) systems integrate document retrieval with large language models.<n>RAG introduces a new privacy risk: adversaries can issue carefully crafted queries to exfiltrate sensitive content gradually.<n>We introduce RAGCRAWLER, which builds a knowledge graph to represent revealed information, and plans queries in semantic space that target unretrieved regions.
  arXiv  Detail & Related papers  (2026-01-22T05:59:42Z)
• The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems [101.68501850486179]
  We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities.<n>This task aims to find imperceptible perturbations that retrieve a target document, originally excluded from the initial top-$k$ candidate set.<n>We propose ReGENT, a reinforcement learning-based framework that tracks interactions between the attacker and the target RAG.
  arXiv  Detail & Related papers  (2025-05-24T08:19:25Z)
• On the Potential of Re-configurable Intelligent Surface (RIS)-assisted Physical Layer Authentication (PLA) [0.0]
  Re-configurable Intelligent Surfaces (RIS) technology is increasingly becoming a potential component for next-generation wireless networks. However, the broadcast nature of RIS-assisted wireless communication makes it vulnerable to malicious attacks at the physical layer. This paper investigates RIS-assisted wireless communication systems to unlock the potential of using RIS for physical layer authentication (PLA)
  arXiv  Detail & Related papers  (2024-05-01T10:17:24Z)
• AIR: Threats of Adversarial Attacks on Deep Learning-Based Information Recovery [3.8556081819690164]
  We investigate adversarial attacks on the SOTA DL-based information recovery model, i.e., DeepReceiver. Extensive experiments show that the DeepReceiver is vulnerable to the designed attack methods in all of the considered scenarios. It can also be found that the DeepReceiver is vulnerable to adversarial perturbations even with very low power and limited PAPR.
  arXiv  Detail & Related papers  (2023-08-17T04:55:02Z)
• Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path [40.4378338001229]
  We study a novel episodic risk-sensitive Reinforcement Learning (RL) problem, named Iterated CVaR RL, which aims to maximize the tail of the reward-to-go at each step. This formulation is applicable to real-world tasks that demand strong risk avoidance throughout the decision process.
  arXiv  Detail & Related papers  (2022-06-06T15:24:06Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)
• Automatic Risk Adaptation in Distributional Reinforcement Learning [26.113528145137497]
  The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes. This is especially important in safety-critical environments, where errors can lead to high costs or damage. We show reduced failure rates by up to a factor of 7 and improved generalization performance by up to 14% compared to both risk-aware and risk-agnostic agents.
  arXiv  Detail & Related papers  (2021-06-11T11:31:04Z)
• Ultra-Reliable Indoor Millimeter Wave Communications using Multiple Artificial Intelligence-Powered Intelligent Surfaces [115.85072043481414]
  We propose a novel framework for guaranteeing ultra-reliable millimeter wave (mmW) communications using multiple artificial intelligence (AI)-enabled reconfigurable intelligent surfaces (RISs) The use of multiple AI-powered RISs allows changing the propagation direction of the signals transmitted from a mmW access point (AP) Two centralized and distributed controllers are proposed to control the policies of the mmW AP and RISs.
  arXiv  Detail & Related papers  (2021-03-31T19:15:49Z)
• Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
  Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs. We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2020-08-05T07:49:42Z)
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations [88.94162416324505]
  A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations deviate from the true states, they can mislead the agent into making suboptimal actions. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, is ineffective for many RL tasks.
  arXiv  Detail & Related papers  (2020-03-19T17:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.