Balancing Privacy and Robustness in Prompt Learning for Large Language Models

Chiyu Shi, Junyu Su, Chiawei Chu, Baoping Wang () and Duanyang Feng
Additional contact information
Chiyu Shi: Faculty of Data Science City, University of Macau, Macau 999078, China
Junyu Su: Faculty of Art and Communication, Kunming University of Science and Technology, Kunming 650032, China
Chiawei Chu: Faculty of Data Science City, University of Macau, Macau 999078, China
Baoping Wang: School of Management, Guangdong University of Science and Technology, Dongguan 523070, China
Duanyang Feng: Faculty of Data Science City, University of Macau, Macau 999078, China

Mathematics, 2024, vol. 12, issue 21, 1-17

Abstract: This paper tackles the critical issue of privacy in Natural Language Processing (NLP) systems that process sensitive data by introducing a novel framework combining differential privacy and adversarial training. The proposed solution ensures formal privacy guarantees by minimizing the influence of individual data points on the model’s behavior, effectively preventing information leakage. Simultaneously, adversarial training is applied to strengthen model robustness against privacy attacks by exposing it to adversarial examples during training. The framework is rigorously evaluated across various NLP tasks, demonstrating its capability to balance privacy preservation with high utility effectively. These results mark a significant advancement in developing secure and reliable NLP systems, particularly for applications requiring stringent data confidentiality, such as healthcare and finance.

Keywords: privacy protextion; large language model; prompt learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/21/3359/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/21/3359/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:21:p:3359-:d:1507162

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().