LLM-PBE: Assessing Data Privacy in Large Language Models
Proceedings of the VLDB Endowment · 2024-07 · 17 (11) · 3201-3214
DOI: 10.14778/3681954.3681994 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 30.08.2024. Verfasst von Qinbin Li und 12 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 91 Literaturangaben.
Abstract (Originalsprache)
Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis. Their profound capabilities in processing and interpreting complex language data, however, bring to light pressing concerns regarding data privacy, especially the risk of unintentional training data leakage. Despite the critical nature of this issue, there has been no existing literature to offer a comprehensive assessment of data privacy risks in LLMs. Addressing this gap, our paper introduces LLM-PBE, a toolkit crafted specifically for the systematic evaluation of data privacy risks in LLMs. LLM-PBE is designed to analyze privacy across the entire lifecycle of LLMs, incorporating diverse attack and defense strategies, and handling various data types and metrics. Through detailed experimentation with multiple LLMs, LLM-PBE facilitates an in-depth exploration of data privacy concerns, shedding light on influential factors such as model size, data characteristics, and evolving temporal dimensions. This study not only enriches the understanding of privacy issues in LLMs but also serves as a vital resource for future research in the field. Aimed at enhancing the breadth of knowledge in this area, the findings, resources, and our full technical report are made available at https://llm-pbe.github.io/, providing an open platform for academic and practical advancements in LLM privacy assessment.
Zitieren
APA
Li, Q., Hong, J., Xie, C., Tan, J., Xin, R., Hou, J., Yin, X., Wang, Z., Hendrycks, D., Wang, Z., Li, B., He, B., & Song, D. (2024). LLM-PBE: Assessing Data Privacy in Large Language Models. Proceedings of the VLDB Endowment, 17(11), 3201-3214. https://doi.org/10.14778/3681954.3681994
Vancouver
Li Q, Hong J, Xie C, Tan J, Xin R, Hou J, et al. LLM-PBE: Assessing Data Privacy in Large Language Models. Proceedings of the VLDB Endowment. 2024;17(11):3201-3214. doi:10.14778/3681954.3681994
BibTeX
@article{Li2024,
author = {Li, Qinbin and Hong, Junyuan and Xie, Chulin and Tan, Jeffrey and Xin, Rachel and Hou, Junyi and Yin, Xavier and Wang, Zhun and Hendrycks, Dan and Wang, Zhangyang and Li, Bo and He, Bingsheng and Song, Dawn},
title = {LLM-PBE: Assessing Data Privacy in Large Language Models},
journal = {Proceedings of the VLDB Endowment},
year = {2024},
volume = {17},
number = {11},
pages = {3201--3214},
doi = {10.14778/3681954.3681994}
}
EUVIMED