forked from 626_privacy/tensorflow_privacy
Add a figure in README for membership inference attack.
PiperOrigin-RevId: 345249792
This commit is contained in:
parent
15515cb0f4
commit
e7c21abb09
2 changed files with 2 additions and 0 deletions
|
@ -213,6 +213,8 @@ import tensorflow_privacy.privacy.membership_inference_attack.plotting as plotti
|
|||
|
||||
figure = plotting.plot_roc_curve(max_auc_attacker.roc_curve)
|
||||
```
|
||||
which would give a figure like the one below
|
||||
![roc_fig](https://github.com/tensorflow/privacy/blob/master/tensorflow_privacy/privacy/membership_inference_attack/codelab_roc_fig.png?raw=true)
|
||||
|
||||
Additionally, we provide funcitonality to convert the attack results into Pandas
|
||||
data frame:
|
||||
|
|
Binary file not shown.
After Width: | Height: | Size: 14 KiB |
Loading…
Reference in a new issue