paper-with-me

홈 › Papers

Locally Differentially Private In-Context Learning

2024-05-07 · Chunyan Zheng, Keke Sun, Wenhao Zhao, Haibo Zhou, Lixin Jiang, Shaoyang Song, Chunlai Zhou

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem with this promising commercial use is that LLMs have been shown to memorize their training data and their prompt data are vulnerable to membership inference attacks (MIA) and prompt leaking attacks. In order to deal with this problem, we treat LLMs as untrusted in privacy and propose a locally differentially private framework of in-context learning(LDP-ICL) in the settings where labels are sensitive. Considering the mechanisms of in-context learning in Transformers by gradient descent, we provide an analysis of the trade-off between privacy and utility in such LDP-ICL for classification. Moreover, we apply LDP-ICL to the discrete distribution estimation problem. In the end, we perform several experiments to demonstrate our analysis results.

📄 PDF Abstract BibTeX arXiv:2405.04032

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context Learning

Similar Papers 제목 키워드 기반

Pan-Private Uniformity Testing

2019-11-04 · Kareem Amin, Matthew Joseph, Jieming Mao

A centrally differentially private algorithm maps raw data to differentially private outputs. In contrast, a locally differentially private algorithm may only access data through public interaction with data holders, and…

Locally Differentially Private (Contextual) Bandits Learning

2020-06-01 · NeurIPS 2020 12 · Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li 외

We study locally differentially private (LDP) bandits learning in this paper. First, we propose simple black-box reduction frameworks that can solve a large family of context-free bandits learning problems with LDP guara…

Multi-Armed BanditsPrivacy Preserving Deep Learning

Instance-Optimal Differentially Private Estimation

2022-10-28 · Audra McMillan, Adam Smith, Jon Ullman

In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy. Unlike worst-case rates, which may be conservative, algorithms that are locally minimax optimal must adapt to …

Decision Tree for Locally Private Estimation with Public Data

2023-09-21 · NeurIPS 2023 11

We propose conducting locally differentially private (LDP) estimation with the aid of a small amount of public data to enhance the performance of private estimation. Specifically, we introduce an efficient algorithm call…

Better Locally Private Sparse Estimation Given Multiple Samples Per User

2024-08-08 · Yuheng Ma, Ke Jia, Hanfang Yang

Previous studies yielded discouraging results for item-level locally differentially private linear regression with $s^*$-sparsity assumption, where the minimax rate for $nm$ samples is $\mathcal{O}(s^{*}d / nm\varepsilon…

regression