先进制造业知识服务平台
国家科技图书文献中心机械分馆　　工信部产业技术基础公共服务平台　　国家中小企业公共服务示范平台

Implementation of a Novel Fully Convolutional Network Approach to Detect and Classify Cyber-Attacks on IoT Devices in Smart Manufacturing Systems
参考中译:智能制造系统中物联网设备网络攻击检测与分类的全卷积网络方法实现


     

文集名：Flexible Automation and Intelligent Manufacturing: The Human-Data-Technology Nexus - Proceedings of FAIM 2022
作者：Mohammad Shahin（The University of Texas at San Antonio）
FFrank Chen（The University of Texas at San Antonio）
Hamed Bouzary（The University of Texas at San Antonio）
Ali Hosseinzadeh（The University of Texas at San Antonio）
Rasoul Rashidifar（The University of Texas at San Antonio）
会议名：31st International Conference on Flexible Automation and Intelligent Manufacturing (FAIM 2022)
会议日期：June 19-23, 2022
会议地点：Detroit, Michigan, USA
出版年：2023
页码：107-114
总页数：8
馆藏号：345884
分类号：TH16-53/L471/(31st-v.1)
关键词：Smart manufacturing；Industrial ioT；Machine learning；Cybersecurity
参考中译：智能制造；工业物联网；机器学习；网络安全
语种：eng
文摘：In recent years, Internet of things (IoT) devices have been widely implemented and industrially improved in manufacturing settings to monitor, collect, analyze, and deliver data. Nevertheless, this evolution has increased the risk of cyberattacks, significantly. Consequently, developing effective intrusion detection systems based on deep learning algorithms has proven to become a dependable intelligence tool to protect Industrial IoT devices against cyber-attacks. In the current study, for the first time, two different classifications and detection long short-term memory (LSTM) architectures were fine-tuned and implemented to investigate cyber-security enhancement on a benchmark Industrial IoT dataset (BoT-IoT) which takes advantage of several deep learning algorithms. Furthermore, the combinations of LSTM with FCN and CNN demonstrated how these two models can be used to accurately detect cyber security threats. A detailed analysis of the performance of the proposed models is provided. Augmenting the LSTM with FCN achieves state-of-the-art performance in detecting cybersecurity threats.
参考中译：近年来，物联网(IoT)设备在制造业环境中得到了广泛实施和行业改进，以监控、收集、分析和交付数据。然而，这种演变显著增加了网络攻击的风险。因此，开发基于深度学习算法的有效入侵检测系统已被证明是保护工业物联网设备免受网络攻击的可靠情报工具。在当前的研究中，首次对两种不同的分类和检测长短期记忆(LSTM)架构进行了微调和实施，以研究基于基准工业物联网数据集(BOT-IoT)的网络安全增强，该数据集利用了几种深度学习算法。此外，LSTM与FCN和CNN的组合展示了这两个模型如何用于准确检测网络安全威胁。对所提模型的性能进行了详细的分析。使用FCN增强LSTM在检测网络安全威胁方面实现了最先进的性能。

注：参考中译为机器自动翻译，仅供参考。



国家科技图书文献中心  全球文献资源网  京ICP备05055788号-26  机械工业信息研究院 2018-2024