Publication Date

1-1-2026

Document Type

Article

Publication Title

Human Centric Computing and Information Sciences

Volume

16

DOI

10.22967/HCIS.2026.16.006

Abstract

Industry 4.0 has transformed industries by accelerating the adoption of artificial intelligence of things (AIoT); however, it has also led to security risks, such as data leakage. Existing data protection research focuses on network layers, whereas application-layer rating systems rely on subjective evaluations, limiting consistency and applicability. This study proposes a scalable and objective AIoT security rating framework that clarifies ambiguities in the five-question rating system of the Korean Intellectual Property Office and unifies fragmented managerial and technical rating systems. By leveraging large language models (LLMs), the framework integrates a security rating model based on 14 impact factors with automated questionnaire generation. A novel percentage-based measurable constraint ensures objectivity and consistency. The fine-tuned Llama 3.1 8B Instruct model, optimized via direct preference optimization, can enhance customization and question relevance. Results across 13 metrics, including G-Eval and Security G-Eval, highlighted its superiority in aligning questions with prompts, thereby improving specificity and clarity over existing LLMs. A user survey validated its effectiveness with a score of 4.1 out of 5 for correlation and answerability, supported by a Cronbach's alpha of 0.878. This study thus introduces a robust and practical AIoT security rating framework, particularly for the manufacturing, healthcare, and transportation domains, reducing subjective biases while improving applicability.

Funding Number

IITP-2025-RS-2023-00266605

Funding Sponsor

Institute for Information and Communications Technology Promotion

Keywords

AIoT-based Questionnaire, Impact Factor Scaling, LLM Alignment, Security G-Eval Metric, Security Rating Questionnaire

Comments

Human-centric Computing and Information Sciences (2026) 16:06
https://doi.org/10.22967/HCIS.2026.16.006

The original publication of this article contained an error in the funding statement. The project number should be corrected to RS-2024-00425650. The authors would like to apologize for any inconvenience caused. The correct funding statement is given below:

This research was supported by the MSIT (Ministry of Science, ICT), Korea, under the Global Research Support Program in the Digital Field program (RS-2024-00425650) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation).

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 3.0 License

Department

Applied Data Science

Download

Share

COinS