针对ICS的增强入侵检测使用MS1DCNN和变压器来解决数据不平衡问题
Yuanlin Zhang1, Lei Zhang1, Xiaoyuan Zheng1
1School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin 300132, China.
Sensors (Basel, Switzerland)
|January 8, 2025
概括
本研究介绍了用于可编程逻辑控制器 (PLC) 网络的先进入侵检测系统 (IDS). 新的双通道模型通过解决数据不平衡和复杂的网络流量,显著提高了工业控制系统 (ICS) 的检测准确性.
科学领域:
- 网络安全 网络安全
- 网络安全 网络安全
- 工业控制系统 工业控制系统
背景情况:
- 网络入侵对工业控制系统 (ICS) 构成重大威胁.
- 现有的入侵检测系统 (IDS) 在可编程逻辑控制器 (PLC) 网络中面临数据不平衡和长尾分布的挑战.
- 对PLC的有效安全性对于保持工业操作的完整性至关重要.
研究的目的:
- 为了提高入侵检测系统 (IDS) 的检测性能,专门用于可编程逻辑控制器 (PLC) 网络.
- 为应对数据不平衡和网络流量数据中长尾分布的挑战.
- 为改进IDS提出一种新的双通道特征提取模型.
主要方法:
- 构建了针对ICS中的PLC的五种攻击类型的数据集.
- 合成少数群体过量抽样技术 (SMOTE) 和边界线-SMOTE用于数据过量抽样.
- 开发了一个双通道模型,集成了一个多尺度的单维卷积神经网络 (MS1DCNN) 和一个减重变压器 (WDTransformer).
- 实施了交叉和焦点损失的联合损失函数,以改善少数类分类.
主要成果:
- 拟议的双通道模型在构建的数据集上实现了95.11%的准确性和95.12%的F1得分.
- 该模型与传统的机器学习和深度学习模型相比,表现出了更高的性能.
- 整合MS1DCNN和WDTransformer有效提取时间特征并捕获远程依赖关系.
- 定制损失函数成功地减少了少数类别中的错误分类.
结论:
- 开发的双通道IDS模型在保护PLC网络免受网络威胁方面取得了重大进展.
- 提出的方法有效地解决了ICS网络安全中的数据不平衡和长尾分布问题.
- 这项研究为提高入侵检测系统在关键工业环境中的检测能力提供了强大的框架.
相关概念视频
Inductively Coupled Plasma-Mass Spectrometry (ICP-MS): Interferences
377
Inductively coupled plasma–mass spectrometry (ICP–MS) is a highly selective and sensitive technique for accurate elemental analysis. Though the analysis of ICP–MS mass spectra is comparatively straightforward, it is affected by spectroscopic and non-spectroscopic interferences. Spectroscopic interferences arise when the plasma contains ionic species with an m/z value the same as the analyte ion. Spectroscopic interference can be categorized as isobaric, polyatomic ions, and...
377
Inductively Coupled Plasma–Mass Spectrometry (ICP–MS): Overview
624
In inductively coupled plasma–mass spectrometry (ICP–MS), an inductively coupled plasma (ICP) torch is used as an atomizer and ionizer. Solid samples are dissolved and volatilized before being introduced into the high-temperature argon plasma, while solution samples are nebulized and passed through the high-temperature argon plasma. Plasma dissociates the analytes and ionizes their component atoms to form a mixture of positive ions and molecular species. The positive ions are then...
624
Survival Tree
57
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
57


