You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: ModelInversion/README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ Contents:
9
9
10
10
### target_model.py
11
11
* Our target model is a simple MLP based on the PyTorch Tutorial form lecture and https://github.com/bentrevett/pytorch-image-classification/blob/master/1_mlp.ipynb and the ATNT-Dataset from https://github.com/harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch.
12
-
* Pre-trained model 'atnt-mlp-model.pth' can be downloaded from https://drive.google.com/file/d/1RI1b7SdLH7pQ0kui1bmxezvSygAiShjo/view?usp=sharing and put in the 'ModelInversion/' folder.
12
+
* Pre-trained model 'atnt-mlp-model.pth' can be downloaded from https://drive.google.com/file/d/10Swb7sddVHNJWqBe3Bx3zaUifSy1it1r/view?usp=sharing and put in the 'ModelInversion/' folder.
13
13
14
14
### model_inversion.py
15
15
We perform a model inversion attack similar to Fredrikson et al. More concrete we perform an reconstruction attack, where given a label we reconstruct an image of the respective class.
0 commit comments