English(EN) When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control System

新的自适应攻击利用批评者意见不合来攻击无线控制系统

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-19 15:59

研究人员开发了一种名为“意见不合引导奖励投毒”（DGRP）的新型自适应奖励投毒攻击，该攻击以基于学习的无线控制系统为目标。该攻击专门利用软Actor-Critic智能体中双重批评者之间的分歧，尤其是在高不确定性状态下。通过破坏奖励信号，DGRP会扭曲价值估计，并将智能体的策略导向次优行为，从而显著降低RIS辅助网络中的性能。 AI

影响突显了强化学习智能体的新漏洞，需要为AI控制系统采取更强大的安全措施。

排序理由详细介绍针对特定AI应用的创新攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍针对特定AI应用的创新攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 100 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Soumaya Cherkaoui · 2026-05-19 15:59

当批评者意见不合时：RIS辅助无线控制系统中的自适应奖励投毒攻击

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 Reco…

本文如何被排名

报道来源 [1]

当批评者意见不合时：RIS辅助无线控制系统中的自适应奖励投毒攻击

相关实体

相关话题