A Case Study on Using Local LLMs for Automated Cybersecurity Analysis
Unknown authors
Sep 2026· Journal of Superintelligence and Computing· 0 citations
TL;DR
This work considers how by leveraging local LLMs to overcome the data privacy and regulatory compliance risks associated with feeding proprietary data into online AI systems, and demonstrates that local LLMs can serve as replacements for formal systems when matching and reproducing text-based threat modeling rules.
Abstract
The use of generative AI technologies in architectural threat modeling automation seems to be a promising alternative to ‘traditional’ formal approaches (e.g., attack-defense trees, domain-specific languages, knowledge graphs, etc.). The main advantage of Large Language Models (LLMs) is that they can work with system and threat descriptions in textual form, skipping the formalization stage required for traditional frameworks.
The work considers how by leveraging local LLMs (i.e., running on enterprise hardware) to overcome the data privacy and regulatory compliance risks associated with feeding proprietary data into online AI systems. Threat modeling was performed via the free Gemma 4 model family on a dataset containing 200 descriptions of containerized applications, and results were compared with those from a formal ontology-driven framework.
The case study demonstrates that local LLMs can serve as replacements for formal systems when matching and reproducing text-based threat modeling rules. The models with 26 and 31 billion (B) parameters can provide adequate metrics (up to 0.975 precision and 0.981 recall for advanced threat models by the 31B LLM with thinking enabled). However, generative AI cannot guarantee metrics as repeatable as those produced by 'strict' automated cybersecurity analysis systems, and it also requires extra computational power for local use to provide rapid threat modeling.
The findings show that LLMs can approximate structured cybersecurity reasoning under controlled representations, but do not apply it robustly, which has important implications for the design and evaluation of AI-assisted security decision-support systems.
Findings show that LLMs can support early stages of the elicitation of security requirements, although human review is still needed, especially to improve or adjust certain aspects of the requirements.
Michail Takaronis, Athanasia Kollarou, G. Kavallieratos et al.· 0 citations
A unifying taxonomy is proposed, cross-cutting challenges including hallucination, prompt injection, and benchmark fragmentation are identified, and open research directions with particular emphasis on multi-agent orchestration design are outlined with particular emphasis on multi-agent orchestration design.
George Fatouros, Konstantinos Mavrogiorgos, Georgios Makridis et al.· Journal of Cybersecurity and...· 0 citations
This paper presents a prototype approach that transforms publicly available attack knowledge from sources such as MITRE ATT&CK and MITRE EMB3D into instances of the Security Abstraction Model (SAM), a domain-specific security metamodel, and outlines future research directions toward continuous, data-driven cybersecurit...
Alexander Fischer, Ramin Tavakoli Kolagari· Proceedings of the ACM/IEEE...· 0 citations
Large Language Models (LLMs) are increasingly used in cybersecurity, where accurate analysis often requires multi-step and context-dependent reasoning over complex and heterogeneous data. However, existing prompting approaches typically focus on eliciting reasoning without explicitly considering how intermediate reason...
Ji-Ling Zhou, Aisvarya Adeseye, Antti Hakkala et al.· arXiv.org· 0 citations
This work surveys recent LLM-based systems across seven core domains and identifies the need for privacy-aware deployment, timely retrieval and knowledge maintenance for emerging threats, process-level evaluation tied to measurable security outcomes, and human oversight within controlled and hybrid automation workflows...
Hanxin Yu, Shahrear Iqbal, E. C. Pinto et al.· International Journal of Inf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.