Evaluation of privacy and security measures when using LLMs for construction management

Brelih, Anja (author), Srdič, Aleksander (author), Klinc, Robert (author)

The rapid integration of Large Language Models (LLMs) into AI-driven project management systems is transforming the construction industry by enhancing efficiency, automation and decision-making. However, the use of LLMs in the processing of sensitive construction documents raises critical privacy and data security concerns. This paper explores the challenges of handling sensitive information with a focus on methods for removing sensitive data from files before they are processed for LLM applications. Before text data is tokenised and integrated into an LLM, it is important to implement pre-processing techniques that ensure data privacy. Sensitive information, such as financial details, personal data and project-specific proprietary content, must be identified and removed or masked at document level. Techniques such as Named Entity Recognition (NER) can be used to identify personally identifiable information, which can then be redacted or replaced with anonymised placeholders. Automated text redaction and metadata removal tools further enhance security by preventing the unintentional disclosure of confidential content. By ensuring that sensitive data is removed before the documents are processed by LLMs, the construction industry can utilise AI-powered tools while adhering to strict data privacy and security standards. This paper evaluates the effectiveness of these pre-processing techniques and discusses their importance for construction project management.

• Language: English
• Keywords: large language models, data privacy, NER, construction management, document pre-processing
• Work type: Article
• Typology: 1.08 - Published Scientific Conference Contribution
• Organization: FGG - Faculty of Civil and Geodetic Engineering
• Publication version: Version of Record
• Year: 2025
• Number of pages: 9 str.
• PID: 20.500.12556/RUL-171577
• UDC: 004.43:624
• DOI: 10.22260/CCC2025/0068
• COBISS.SI-ID: 246892035
• Publication date in RUL: 28.08.2025

Record is a part of a monograph

• Title: CCC 2025 - Zadar, Croatia : proceedings of the 14th Creative Construction Conference
• Editors: Miroslaw J. Skibniewski, Miklós Hajdú, Žiga Turk
• Place of publishing: [Zadar]
• Publisher: International Association for Automation and Robotics in Construction (IAARC)
• Year: 2025
• COBISS.SI-ID: 246885635
• Collection title: Proceedings of the ... ISARC
• Collection ISSN: 2413-5844

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: veliki jezikovni modeli, zasebnost podatkov, NER, operativno gradbeništvo, predobdelava dokumentov

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P2-0210
• Name: E-Gradbeništvo