Private Fine-tuning of Large Language Models with Zeroth-order Optimization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916591148466176 |
|---|---|
| author | Tang, Xinyu Panda, Ashwinee Nasr, Milad Mahloujifar, Saeed Mittal, Prateek |
| author_facet | Tang, Xinyu Panda, Ashwinee Nasr, Milad Mahloujifar, Saeed Mittal, Prateek |
| contents | Differentially private stochastic gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner, but has proven difficult to scale to the era of foundation models. We introduce DP-ZO, a private fine-tuning framework for large language models by privatizing zeroth order optimization methods. A key insight into the design of our method is that the direction of the gradient in the zeroth-order optimization we use is random and the only information from training data is the step size, i.e., a scalar. Therefore, we only need to privatize the scalar step size, which is memory-efficient. DP-ZO provides a strong privacy-utility trade-off across different tasks, and model sizes that are comparable to DP-SGD in $(\varepsilon,δ)$-DP. Notably, DP-ZO possesses significant advantages over DP-SGD in memory efficiency, and obtains higher utility in $\varepsilon$-DP when using the Laplace mechanism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04343 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Private Fine-tuning of Large Language Models with Zeroth-order Optimization Tang, Xinyu Panda, Ashwinee Nasr, Milad Mahloujifar, Saeed Mittal, Prateek Machine Learning Computation and Language Cryptography and Security Differentially private stochastic gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner, but has proven difficult to scale to the era of foundation models. We introduce DP-ZO, a private fine-tuning framework for large language models by privatizing zeroth order optimization methods. A key insight into the design of our method is that the direction of the gradient in the zeroth-order optimization we use is random and the only information from training data is the step size, i.e., a scalar. Therefore, we only need to privatize the scalar step size, which is memory-efficient. DP-ZO provides a strong privacy-utility trade-off across different tasks, and model sizes that are comparable to DP-SGD in $(\varepsilon,δ)$-DP. Notably, DP-ZO possesses significant advantages over DP-SGD in memory efficiency, and obtains higher utility in $\varepsilon$-DP when using the Laplace mechanism. |
| title | Private Fine-tuning of Large Language Models with Zeroth-order Optimization |
| topic | Machine Learning Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2401.04343 |