Skip to content

xziyue/robust_mnist_feature_py

master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Analyzing Robust Features From MNIST

website: https://github.com/xziyue/robust_mnist_feature_py

TODOs:

  • Implement robust training

  • Implement a sufficient amount of perturbation

  • Compare performance of std model and robust model

  • Implement gradient descent for reconstructing features

Current Problems

  • Convergence: the robust model does not seem to converge well (may need to pretrain the model first)

  • Why does horizontal lines hurt accuracy more significantly than vertical lines?

Goals

  • Is it possible to synthesize "robust" features directly?
  • Is it possible to differentiate nonrobust and robust features blindly?
  • Is is possible to create perturbation that leads to human-readable robust features?

The dataset

The MNIST datset is available at http://yann.lecun.com/exdb/mnist/.

If you would like to run this script on your computer, go to /dataset folder and uncompress all the dataset files to that folder.

Test results

The perturbated image samples can be seen in figure below. The last column is ground truth. The group IDs correspond to the order of images in the figure.

perturbated image samples

Group Id Std Accuracy Robust Accuracy
1 0.829 0.968
2 0.549 0.967
3 0.808 0.969
4 0.727 0.950
5 0.977 0.972

Running standard training over reconstructed datasets:

Group Id Robust Accuracy Nonrobust Accuracy
1 0.792 0.856
2 0.822 0.434
3 0.908 0.865
4 0.876 0.657
5 0.960 0.954

Reconstruction

The reconstructed features can be downloaded from this repo.

Original Reconstruction (Robust) Reconstruction (Nonrobust)

Noise Cancellation on Features

Denoised Robust Features Denoised Nonrobust Features

File description:

Remember to add the root dir to PYTHONPATH.

I am doing a bunch of crazy experiments right now, there are many undocumented files in the repo.

  • util folder:
    • perturbation.py: creates and manages perturbations
    • load_mnist.py: loading data from MNIST idx format (need to correct endianess if the data format has sizes greater than 1 byte)
  • train folder: neural network training scripts
    • train_std_model.py: trains standard model
    • train_pretrained_model: trains a pretrain model as initial weights for robust model
    • train_robust_model.py: trains the robust model
  • test folder: test the performance of models
    • test_std_model: tests the performance of std model on adversarial dataset
    • test_robust_model: tests the performance of robust model on adversarial dataset
  • reconstruct folder: reconstructing the features from models
  • misc folder: some ongoing experiments

References

  • Ilyas, Andrew, et al. "Adversarial examples are not bugs, they are features." arXiv preprint arXiv:1905.02175 (2019).

About

Properties of robust and non-robust features

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages