Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems
This work addresses the need for tools to support cybersecurity experts and engineers in risk assessment for safety-critical domains like forestry, where data privacy limits external sharing, though it is incremental as it applies existing LLM methods to a new domain.
This paper tackled the problem of high workload for cybersecurity experts in safety-critical systems by exploring the use of locally hosted large language models (LLMs) with retrieval-augmented generation to support risk assessment in forestry cyber-physical systems, demonstrating that LLMs can assist experts in generating initial assessments, identifying threats, and providing redundancy checks based on a design science study with 12 experts.
In safety-critical software systems, cybersecurity activities become essential, with risk assessment being one of the most critical. In many software teams, cybersecurity experts are either entirely absent or represented by only a small number of specialists. As a result, the workload for these experts becomes high, and software engineers would need to conduct cybersecurity activities themselves. This creates a need for a tool to support cybersecurity experts and engineers in evaluating vulnerabilities and threats during the risk assessment process. This paper explores the potential of leveraging locally hosted large language models (LLMs) with retrieval-augmented generation to support cybersecurity risk assessment in the forestry domain while complying with data protection and privacy requirements that limit external data sharing. We performed a design science study involving 12 experts in interviews, interactive sessions, and a survey within a large-scale project. The results demonstrate that LLMs can assist cybersecurity experts by generating initial risk assessments, identifying threats, and providing redundancy checks. The results also highlight the necessity for human oversight to ensure accuracy and compliance. Despite trust concerns, experts were willing to utilize LLMs in specific evaluation and assistance roles, rather than solely relying on their generative capabilities. This study provides insights that encourage the use of LLM-based agents to support the risk assessment process of cyber-physical systems in safety-critical domains.