Back to Home

Request Correction

Use this form to request corrections to the paper metadata. Select the fields that need correction and provide the correct information.

Correction Guidelines

  1. Click the edit button next to a field to report a correction.
  2. Fill in the suggested correction value for each field you want to correct.
  3. Provide your name and email so we can contact you if needed.

Paper Information

lrec2024-main-0935

Locally Differentially Private In-Context Learning

Paper Fields

Click the edit button next to a field to report a correction.

Title

Locally Differentially Private In-Context Learning

Abstract

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


Authors

Expand an author to correct their information. Use the remove button to request author removal, or add a new author.


PDF Attachment

You may attach a PDF as a corrected version of the paper. Max file size: 10MB. Only PDF files are accepted.

Drag & drop a PDF here, or click to select

Your Information

Author Declaration *

Select at least one field to correct using the edit buttons above.