Detail publikačního výsledku

Analyzing anomalies in industrial networks: A data-driven approach to enhance security in manufacturing processes

KUCHAŘ, K.; FUJDIAK, R.

Originální název

Analyzing anomalies in industrial networks: A data-driven approach to enhance security in manufacturing processes

Anglický název

Analyzing anomalies in industrial networks: A data-driven approach to enhance security in manufacturing processes

Druh

Článek WoS

Originální abstrakt

Industrial networks are adapted to their specific requirements, especially in terms of industrial processes. To ensure sufficient security in these networks, it is necessary to set and use security policies that complement government regulations, recommendations, and relevant security standards. This paper aims to provide an in-depth analysis of the anomalies occurring within the networks and propose a structure for collecting valuable data from the experimental site based on dividing anomalies into three main categories: security, operational, and service anomalies (and regular traffic recognition). We present a proof-of-concept solution/design aggregating data in industrial networks for advanced anomaly classification. Multiple data sources such as industrial communication, sensor data (additional sensors controlling device behavior), and HW status data are used as data sources. A total of three scenarios (using a physical testbed) were implemented, where we achieved an accuracy of 0.8541/0.9972 in advanced anomaly classification.

Anglický abstrakt

Industrial networks are adapted to their specific requirements, especially in terms of industrial processes. To ensure sufficient security in these networks, it is necessary to set and use security policies that complement government regulations, recommendations, and relevant security standards. This paper aims to provide an in-depth analysis of the anomalies occurring within the networks and propose a structure for collecting valuable data from the experimental site based on dividing anomalies into three main categories: security, operational, and service anomalies (and regular traffic recognition). We present a proof-of-concept solution/design aggregating data in industrial networks for advanced anomaly classification. Multiple data sources such as industrial communication, sensor data (additional sensors controlling device behavior), and HW status data are used as data sources. A total of three scenarios (using a physical testbed) were implemented, where we achieved an accuracy of 0.8541/0.9972 in advanced anomaly classification.

Klíčová slova

Neural networks (NN); Anomaly; Anomaly classification; Sensory data; Cybersecurity; Industrial Control System (ICS); Operational Technology (OT)

Klíčová slova v angličtině

Neural networks (NN); Anomaly; Anomaly classification; Sensory data; Cybersecurity; Industrial Control System (ICS); Operational Technology (OT)

Autoři

KUCHAŘ, K.; FUJDIAK, R.

Rok RIV

2026

Vydáno

28.02.2025

ISSN

0167-4048

Periodikum

COMPUTERS & SECURITY

Svazek

153

Číslo

June 2025

Stát

Spojené království Velké Británie a Severního Irska

Strany od

1

Strany do

15

Strany počet

15

URL

https://www.sciencedirect.com/science/article/pii/S0167404825000847?utm_campaign=STMJ_219742_AUTH_SERV_PA&utm_medium=email&utm_acid=277298152&SIS_ID=&dgcid=STMJ_219742_AUTH_SERV_PA&CMX_ID=&utm_in=DM547969&utm_source=AC_

BibTex

@article{BUT197746,
  author="Karel {Kuchař} and Radek {Fujdiak}",
  title="Analyzing anomalies in industrial networks: A data-driven approach to enhance security in manufacturing processes",
  journal="COMPUTERS & SECURITY",
  year="2025",
  volume="153",
  number="June 2025",
  pages="1--15",
  doi="10.1016/j.cose.2025.104395",
  issn="0167-4048",
  url="https://www.sciencedirect.com/science/article/pii/S0167404825000847?utm_campaign=STMJ_219742_AUTH_SERV_PA&utm_medium=email&utm_acid=277298152&SIS_ID=&dgcid=STMJ_219742_AUTH_SERV_PA&CMX_ID=&utm_in=DM547969&utm_source=AC_"
}