626_privacy/tensorflow_privacy
2
0
Fork 1
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions

Prettier README

Browse source
This commit is contained in:
Nicholas Carlini 2021-12-14 00:54:29 +00:00
parent 7e40ad9704
commit a41549d103
1 changed files with 21 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
research/mi_lira_2021/README.md
View file

@ -1,3 +1,5 @@
## Membership Inference Attacks From First Principles
This directory contains code to reproduce our paper: This directory contains code to reproduce our paper:
**"Membership Inference Attacks From First Principles"** **"Membership Inference Attacks From First Principles"**
@ -112,3 +114,16 @@ where the global threshold attack is the baseline, and our online,
online-with-fixed-variance, offline, and offline-with-fixed-variance online-with-fixed-variance, offline, and offline-with-fixed-variance
attack variants are the four other curves. Note that because we only attack variants are the four other curves. Note that because we only
train a few models, the fixed variance variants perform best. train a few models, the fixed variance variants perform best.
### Citation
You can cite this paper with
```
@article{carlini2021membership,
title={Membership Inference Attacks From First Principles},
author={Carlini, Nicholas and Chien, Steve and Nasr, Milad and Song, Shuang and Terzis, Andreas and Tramer, Florian},
journal={arXiv preprint arXiv:2112.03570},
year={2021}
}
```