Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913658431340544 |
|---|---|
| author | Shi, Haonan Ouyang, Tu Wang, An |
| author_facet | Shi, Haonan Ouyang, Tu Wang, An |
| contents | Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients' data privacy requirements, and tuning costs. While recent approaches like split learning and offsite tuning demonstrate promising architectures for privacy-preserving fine-tuning, there is a gap in systematically addressing the multidimensional trade-offs required for diverse real-world deployments. We propose several indicative evaluation metrics to guide design trade-offs for privacy-preserving fine-tuning and a series of example designs, collectively named GuardedTuning; they result from novel combinations of system architectures with adapted privacy-enhancement methods and emerging computation techniques. Each design represents distinct trade-offs across model utility, privacy guarantees, and costs. Experimental results demonstrate that these designs protect against data reconstruction attacks while maintaining competitive fine-tuning performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04323 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models Shi, Haonan Ouyang, Tu Wang, An Machine Learning Cryptography and Security Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients' data privacy requirements, and tuning costs. While recent approaches like split learning and offsite tuning demonstrate promising architectures for privacy-preserving fine-tuning, there is a gap in systematically addressing the multidimensional trade-offs required for diverse real-world deployments. We propose several indicative evaluation metrics to guide design trade-offs for privacy-preserving fine-tuning and a series of example designs, collectively named GuardedTuning; they result from novel combinations of system architectures with adapted privacy-enhancement methods and emerging computation techniques. Each design represents distinct trade-offs across model utility, privacy guarantees, and costs. Experimental results demonstrate that these designs protect against data reconstruction attacks while maintaining competitive fine-tuning performance. |
| title | Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2501.04323 |