PulseAugur
实时 12:17:33
English(EN) Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Grids

新的防御方法增强了深度神经网络抵御电网网络攻击的能力

研究人员开发了一种名为伪特征填充(Pseudo-Feature Padding)的新型防御机制,用于保护网络物理系统(CPS)中使用的深度神经网络(DNN)免受虚假数据注入攻击(FDIA)的侵害。这种轻量级、模型无关的方法引入了一个额外的输入层,该层根据输入的统计分布从输入样本中随机填充伪特征值。这种随机化使得对抗性攻击在计算上不可行,并在不改变核心DNN架构的情况下增强了模型的鲁棒性。该框架在电网应用中得到了成功测试,证明了模型在攻击下的韧性得到了显著提高,同时对性能的影响最小。 AI

影响 增强了部署在电网等关键基础设施中的AI系统的安全性。

排序理由 该集群包含一篇详细介绍DNN抵御网络攻击的新防御机制的研究论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的防御方法增强了深度神经网络抵御电网网络攻击的能力

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Farhin Farhad Riya, Shahinul Hoque, Yingyuan Yang, Jinyuan Sun, Kevin Tomsovic ·

    Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Grids

    arXiv:2606.20415v1 Announce Type: new Abstract: Deep Neural Networks DNNs have achieved remarkable accuracy in various tasks including their application in CyberPhysical Systems CPS for detecting False Data Injection Attacks FDIA during critical operations However the unique infr…

  2. arXiv cs.LG TIER_1 English(EN) · Kevin Tomsovic ·

    Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Grids

    Deep Neural Networks DNNs have achieved remarkable accuracy in various tasks including their application in CyberPhysical Systems CPS for detecting False Data Injection Attacks FDIA during critical operations However the unique infrastructure of CPS makes DNNs vulnerable to explo…