The research proposes the application of Digital Intelligent Assistants (DIAs) as proactive agents that can support employees in dealing with cybersecurity issues in sustainable industrial processes underlying the importance of a fruitful Human-Artificial Intelligence collaboration. Cyber-attacks around the world are constantly increasing. DIAs are becoming more effective, also thanks to the use of Large Language Models. Users are required to recall security procedures and rules. Moreover, attacks are constantly evolving and following different patterns. The study presents how a DIA can be a backup agent during and after an attack. The application of digital intelligent assistance technology helps to reduce the cognitive load and pressure that users feel during downtime. In addition, the solution enhances attack reporting by decreasing the shame experienced by the victims. The research proposes a methodological design defining the agent's technical and functional characteristics and its adaptive relationship with human characteristics. The solution is developed using the RASA framework and evaluated through a case study based on a phishing attack scenario.

Application of a digital intelligent assistant to support industrial processes: the case of adaptive allocation in the face of cyber attacks

Colabianchi, Silvia
2025-01-01

Abstract

The research proposes the application of Digital Intelligent Assistants (DIAs) as proactive agents that can support employees in dealing with cybersecurity issues in sustainable industrial processes underlying the importance of a fruitful Human-Artificial Intelligence collaboration. Cyber-attacks around the world are constantly increasing. DIAs are becoming more effective, also thanks to the use of Large Language Models. Users are required to recall security procedures and rules. Moreover, attacks are constantly evolving and following different patterns. The study presents how a DIA can be a backup agent during and after an attack. The application of digital intelligent assistance technology helps to reduce the cognitive load and pressure that users feel during downtime. In addition, the solution enhances attack reporting by decreasing the shame experienced by the victims. The research proposes a methodological design defining the agent's technical and functional characteristics and its adaptive relationship with human characteristics. The solution is developed using the RASA framework and evaluated through a case study based on a phishing attack scenario.
2025
adaptive automation
chatbot
cybersecurity
industry 4.0
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12606/24134
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
social impact