arXiv cs.AI· Vita Santa Barletta, Danilo Caivano, Gabriel Cellammare, Andrea Dimauro, Pasquale Mesagna, Massimiliano Morga·· 12 小时前AI 评分24
用数字孪生与 LLM 量化网络-社会影响的新框架
A Digital Twin to Improve Cyber-Social Impact
AI 导读
一篇论文提出将数字孪生与 Cyber-Social Security 模型结合，用 Mininet 和 MiniCPS 构建虚拟化工控系统（ICS）环境模拟攻击场景。其核心指标 CSVSS 在 CVSS 基础上增加基于 Entity 与 Place 支柱的社会影响维度，输出单一可复现的严重性评分。框架由 LLM 完成首轮漏洞映射与风险报告草拟，人类分析师借助可解释 AI 反馈保留关键决策权。
正文 · 原文
Abstract:The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has significantly expanded the cyber threat landscape. Traditional cybersecurity models, primarily based on the Confidentiality, Integrity, and Availability (CIA triad), fail to capture the broader societal and operational impacts of cyberattacks. This paper proposes a novel framework that integrates Digital Twin technology with a Cyber-Social Security model to simulate, analyze, and quantify cyber threats in critical infrastructures. Virtualized ICS environments built with Mininet and MiniCPS are used to model attack scenarios and assess their consequences across technical and social dimensions. At the core of the framework lies the Cyber-Social Vulnerability Scoring System (CSVSS), a quantitative metric that extends CVSS with a Social Impact dimension grounded in the Entity and Place pillars, producing a single, reproducible severity score that reflects real-world consequences. Crucially, the framework does not automate risk assessment but keeps the human analyst at its center: a Large Language Model (LLM) performs a first-pass analysis, mapping vulnerabilities and drafting risk reports, while the analyst, supported by explainable AI feedback, validates the findings and retains decision authority over critical cases. Experimental results demonstrate the framework's ability to model and score cyber-social impact, while the human-in-the-loop design is presented as a conceptual principle to preserve oversight.
| Comments: | 16 pages, 5 figures |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28430 [cs.CR] |
| (or arXiv:2610.28430v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28430 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | SHIELD-AI co-located in European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - ECML PKDD 2026 |
Submission history
From: Vita Santa Barletta [view email]
[v1]
Tue, 20 Oct 2026 15:58:33 UTC (3,304 KB)
来源：arXiv cs.AI · arxiv.org