Smart Meter Modbus RS-485 Intrusion Detection by Federated Learning Approach

Hossain, Md. Delwar; Ochiai, Hideya; Khan, Latifur; Kadobayashi, Youki

doi:10.1109/iccae56788.2023.10111132

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All experiments are conducted on TensorFlow-GPU-2.7.0 with Python 3.9 running on Intel i7-11700 CPU and NVIDIA RTX4060-16G GPU. To fully evaluate the proposed strategy, we select three typical datasets for experimental validation, namely Smart Meters [16], NSL-KDD [17], and UNSW-NB15 [18]. The fundamental characteristics of these datasets are described in Table 2.…”

Section: Experimental Results and Analysis A Experiments Settingsmentioning

confidence: 99%

“…Furthermore, the proposed LSFL anomaly detection strategy with RMS-CNN, denoted as RMS-CNN-LSFL, is compared with two benchmark strategies denoted as CNN-FL and MLP-FL. Herein, CNN-FL is a distributed federal learning anomaly detection strategy based on 1D-CNN with GRU [11] while MLP-FL is a similar strategy based on MLP network [16].…”

Section: Experimental Results and Analysis A Experiments Settingsmentioning

confidence: 99%

See 1 more Smart Citation

End-Edge Collaborative Lightweight Secure Federated Learning for Anomaly Detection of Wireless Industrial Control Systems

Xu,

Du,

et al. 2024

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

With the wide applications of industrial wireless network technologies, industrial control system (ICS) is evolving from wired and centralized to wireless and distributed, during which eavesdropping and attacking become serious problems. To guarantee the security of wireless and distributed ICS, this paper establishes an end-edge collaborative lightweight secure federated learning (LSFL) architecture and proposes a LSFL anomaly detection strategy. Specifically, we first design a residual multi-head self-attention convolutional neural network for local feature learning, where the variability and dependency of spatial-temporal features can be sufficiently evaluated. Then, to reduce the wireless communication cost for parameter exchange and edge federal learning, we propose a dynamic parameter pruning algorithm by evaluating the contribution of each parameter based on the information entropy gain. Furthermore, to ensure the parameter security during wireless transmission in the open radio environment, we propose an adaptive key generation algorithm for parameter encryption. Finally, the proposed strategy is experimentally validated on representative datasets, including Smart Meter, NSL-KDD, and UNSW-NB15. Experimental results demonstrate that the proposed strategy achieves 99% accuracy on different datasets, where at least 89.6% wireless communication cost is reduced and tampering/injecting attacks are defended.INDEX TERMS Industrial control system, anomaly detection, federated learning, convolutional neural network.

show abstract

Section: Experimental Results and Analysis A Experiments Settingsmentioning

confidence: 99%

Section: Experimental Results and Analysis A Experiments Settingsmentioning

confidence: 99%

End-Edge Collaborative Lightweight Secure Federated Learning for Anomaly Detection of Wireless Industrial Control Systems

Xu,

Du,

et al. 2024

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

show abstract

“…The work helps to strengthen training in key areas for the industrial sector and promotes practical and applied training of great importance for the training of engineers and technicians in the field of industrial automation and communication. According to [ 32 ], in the midst of various CPS entities, AMI (Advanced Metering Infrastructure), i.e., the smart grid, is among the most important entities essential for the rapid transformation of CPS, where Modbus protocol (RS-485) is commonly used in smart meters for communication on the physical layer. The Modbus Attack DataSet for AMI (MAMI) is experimented on, and the authors’ results demonstrate that the FL design approach is remarkably efficient in identifying critical smart meter assaults.…”

Section: Related Workmentioning

confidence: 99%

Modbus Extension Server Implementation for BIoT-Enabled Smart Switch Embedded System Device

Găitan,

Zagan

2024

Sensors

View full text Add to dashboard Cite

The industrial control and automation sector has invested in the development and standardization of new wireless (WirelessHART, ISA 100.11a, and WIA-PA) and wired (Profibus/Profinet, Modbus, and LonWORK) solutions aimed at automating processes to support standard monitoring and control functions from the perspective of addressing critical applications, as well as those integrated within the Building Internet of Things (BIoT) concept. Distributed data acquisition and control systems allow modern installations to monitor and control devices remotely. Various network protocols have been proposed to specify communication formats between a client/gateway and server devices, with Modbus being an example that has been widely implemented in the latest industrial electrical installations. The main contribution made in this paper concerns the completion of the Modbus Extension (ModbusE) specifications for the server station in the classical Modbus communication architecture, as well as their implementation and testing in an STM32F4 kit. A general-purpose control architecture is proposed for BIoT sector, comprising both intelligent touch switches and communication protocols of which the Modbus protocol is used extensively for the monitoring and control part, especially between clients, smart switches, and devices. The specific contributions concern the presentation of a scientific and practical implementation of improved specifications and their integration as software modules on ModbusE protocol server stations. A client station with a VirtualComm USB PC connection is also implemented in the lab to test the operation of the proposed server with specific Modbus applications.

show abstract