Assessment Methods and Protection Strategies for Data Leakage Risks in Large Language Models
Journal of Industrial Engineering and Applied Science · 2025
DOI: 10.70393/6a69656173.323736 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Industrial Engineering and Applied Science, 2025. Verfasst von Xingpeng Xiao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, yet their inherent vulnerabilities to data leakage pose significant security and privacy risks. This paper presents a comprehensive analysis of assessment methods and protection strategies for addressing data leakage risks in LLMs. A systematic evaluation framework is proposed, incorporating multi-dimensional risk assessment models and quantitative metrics for vulnerability detection. The research examines various protection mechanisms across different stages of the LLM lifecycle, from data pre-processing to post-deployment monitoring. Through extensive analysis of protection techniques, the study reveals that integrated defense strategies combining gradient protection, query filtering, and output sanitization achieve optimal security outcomes, with risk reduction rates exceeding 95%. The implementation of these protection mechanisms demonstrates varying effectiveness across different operational scenarios, with performance impacts ranging from 8% to 18%. The research contributes to the field by establishing standardized evaluation criteria and proposing enhanced protection strategies that balance security requirements with system performance. The findings provide valuable insights for developing robust security frameworks in LLM deployments, while identifying critical areas for future research in adaptive defense mechanisms and scalable protection solutions.
Zitieren
APA
Xiao, X., Zhang, Y., Xu, J., Ren, W., & Zhang, J. (2025). Assessment Methods and Protection Strategies for Data Leakage Risks in Large Language Models. Journal of Industrial Engineering and Applied Science. https://doi.org/10.70393/6a69656173.323736
Vancouver
Xiao X, Zhang Y, Xu J, Ren W, Zhang J. Assessment Methods and Protection Strategies for Data Leakage Risks in Large Language Models. Journal of Industrial Engineering and Applied Science. 2025. doi:10.70393/6a69656173.323736
BibTeX
@article{Xiao2025,
author = {Xiao, Xingpeng and Zhang, Yaomin and Xu, Jian and Ren, Wenkun and Zhang, Junyi},
title = {Assessment Methods and Protection Strategies for Data Leakage Risks in Large Language Models},
journal = {Journal of Industrial Engineering and Applied Science},
year = {2025},
doi = {10.70393/6a69656173.323736}
}
EUVIMED