SafeMan: A unified framework to manage cybersecurity and safety in manufacturing industry

Abstract

Summary Industrial control systems (ICS) are considered cyber‐physical systems that join both cyber and physical worlds. Due to their tight interaction, where humans and robots co‐work and co‐inhabit in the same workspaces and production lines, cyber‐attacks targeting ICS can alter production processes and even bypass safety procedures. As an example, these cyber‐attacks could interrupt physical industrial processes and cause potential injuries to workers. In this article, we present SafeMan, a unified management framework based on the Edge Computing paradigm that provides high‐performance applications for the detection and mitigation of both cyber‐attacks and safety threats in industrial scenarios. Three use cases show specific threats in manufacturing as well as the SafeMan actions carried out to detect and mitigate them. In order to validate our proposal, a pool of experiments was performed with Electra, an industrial dataset with normal network traffic and different cyber‐attacks by using a given number of Modbus TCP and S7Comm devices. The experiments measured the runtime performance of anomaly detection techniques based on machine learning and deep learning to detect cyber‐attacks in control networks. The experimental results show that Neural Networks report the best performance, being able to examine 217 feature vectors per second over Electra, and therefore demonstrating that it can be used as detection model for SafeMan in real scenarios.

Rage against robots: Emotional and motivational dimensions of anti-robot attacks, robot sabotage, and robot bullying

“…Security breaches are another form of attacks on robots, which may not be clearly visible immediately after the attacks but may cause dramatic consequences affecting the operations of the robots and the safety of humans (Oravec, 2017;Perales Gómez et al, 2021). A security breach can allow for the reprogramming of a robot in the future in ways that would produce unexpected or rogue behavior on the part of the robot (Maggi et al, 2017).…”

An interpretable semi‐supervised system for detecting cyberattacks using anomaly detection in industrial scenarios

“…The authors studied the performance of RF, SVM, OC‐SVM, Isolation Forest (IF), and FCNN, concluding that the models that achieved the highest performance was SVM and RF. Besides, the same authors presented another study comparing the performance of these models in terms of time evaluation [24]. The conclusion was that FCNN outperforms the other models.…”

A Survey on Industrial Control System Testbeds and Datasets for Security Research

“…On the other hand, the semi-supervised OCSVM performed properly on both the dataset, reaching 0.996 of Precision in Electra S7Comm. In the successive year, the same authors proposed SafeMan [230], a framework to manage both cybersecurity and safety in the manufacturing industry. It is composed of a set of applications and services used to monitor and analyze the industrial process in real-time.…”