ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks
Yu Lin, Ruining Yang, Yunlong Mao, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyu Chen, Bing Duan, Sheng Zhong. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Qizhi Zhang (ORCID: https://orcid.org/0000-0002-8544-609X)
- Yu‐Pin Lin (ORCID: https://orcid.org/0000-0003-1954-334X)
- Huiqi Liu (ORCID: https://orcid.org/0000-0003-1879-0779)
- Sheng Zhong (ORCID: https://orcid.org/0000-0003-2865-8202)
- Quanwei Cai
- Yunlong Mao (ORCID: https://orcid.org/0000-0001-9024-9544)
- Bing Duan (ORCID: https://orcid.org/0000-0001-5324-9393)
- Ye Wu (ORCID: https://orcid.org/0000-0002-8643-4023)
- Zhiyu Chen (ORCID: https://orcid.org/0000-0002-9707-3390)
- Ruining Yang
- Jue Hong
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.58
- Primary Topic
- Privacy-Preserving Technologies in Data
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- City University of Hong Kong
- National Natural Science Foundation of China
- Government of Jiangsu Province
- Tsinghua University
- Fundamental Research Funds for the Central Universities