Skip to content

TrustAIRLab/ICL-MIA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Membership Inference Attacks Against In-Context Learning

The repository contains the code for the paper "Membership Inference Attacks Against In-Context Learning," where we investigate the vulnerability of in-context learning. The code is designed for the GPT2-XL model, but it can be easily adapted to other models.

For questions or issues, feel free to open an issue or contact us at rui.wen@cispa.de.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages