Abstract
Numerous studies have highlighted the privacy risks associated with large language models. Our research offers a unique perspective by demonstrating that pretrained large language models can effectively contribute to privacy preservation. We propose a locally differentially private mechanism called DP-Prompt, which leverages the power of pretrained large language models and zero-shot prompting to counter author de-anonymization attacks while minimizing the impact on downstream utility. When DP-Prompt is used with a powerful language model like ChatGPT (gpt-3.5), we observe a notable reduction in the success rate of de-anonymization attacks, showing that it surpasses existing approaches by a considerable margin despite its simpler design. For instance, in the case of the IMDB dataset, DP-Prompt (with ChatGPT) perfectly recovers the clean sentiment F1 score while achieving a 46% reduction in author identification F1 score against static attackers and a 26% reduction against adaptive attackers. We conduct extensive experiments across six open-source large language models, ranging up to 7 billion parameters, to analyze various effects of the privacy-utility tradeoff.- Anthology ID:
- 2023.findings-emnlp.566
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8442–8457
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.566
- DOI:
- 10.18653/v1/2023.findings-emnlp.566
- Cite (ACL):
- Saiteja Utpala, Sara Hooker, and Pin-Yu Chen. 2023. Locally Differentially Private Document Generation Using Zero Shot Prompting. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8442–8457, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Locally Differentially Private Document Generation Using Zero Shot Prompting (Utpala et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.566.pdf