MadryLab/mnist_challenge_models MadryLab/mnist_challenge_models

  • Stars
    star
    1
  • Language
  • License
    MIT License
  • Created over 7 years ago
  • Updated about 6 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
MadryLab/mnist_challenge_models
github

MadryLab

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

More Repositories

1

robustness

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
Jupyter Notebook
905
star
2

mnist_challenge

A challenge to explore adversarial robustness of neural networks on MNIST.
Python
720
star
3

cifar10_challenge

A challenge to explore adversarial robustness of neural networks on CIFAR10.
Python
488
star
4

photoguard

Raising the Cost of Malicious AI-Powered Image Editing
Jupyter Notebook
419
star
5

constructed-datasets

Datasets for the paper "Adversarial Examples are not Bugs, They Are Features"
178
star
6

trak

A fast, effective data attribution method for neural networks in PyTorch
Python
169
star
7

robust_representations

Code for "Learning Perceptually-Aligned Representations via Adversarial Robustness"
Jupyter Notebook
158
star
8

backgrounds_challenge

Python
134
star
9

robustness_applications

Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"
Jupyter Notebook
125
star
10

implementation-matters

Python
104
star
11

EditingClassifiers

Python
95
star
12

robust-features-code

Code for "Robustness May Be at Odds with Accuracy"
Jupyter Notebook
91
star
13

datamodels-data

Data for "Datamodels: Predicting Predictions with Training Data"
Python
64
star
14

blackbox-bandits

Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"
Python
61
star
15

BREEDS-Benchmarks

Jupyter Notebook
50
star
16

cox

A lightweight experimental logging library
Python
50
star
17

adversarial_spatial

Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.
Python
49
star
18

modeldiff

ModelDiff: A Framework for Comparing Learning Algorithms
Jupyter Notebook
44
star
19

failure-directions

Distilling Model Failures as Directions in Latent Space
Jupyter Notebook
42
star
20

smoothed-vit

Certified Patch Robustness via Smoothed Vision Transformers
Python
41
star
21

label-consistent-backdoor-code

Code for "Label-Consistent Backdoor Attacks"
Python
40
star
22

dataset-interfaces

Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
Jupyter Notebook
39
star
23

DebuggableDeepNetworks

Jupyter Notebook
37
star
24

data-transfer

Python
31
star
25

ImageNetMultiLabel

Fine-grained ImageNet annotations
Jupyter Notebook
28
star
26

relu_stable

Python
26
star
27

spatial-pytorch

Codebase for "Exploring the Landscape of Spatial Robustness" (ICML'19, https://arxiv.org/abs/1712.02779).
Jupyter Notebook
26
star
28

dataset-replication-analysis

Jupyter Notebook
25
star
29

backdoor_data_poisoning

Python
25
star
30

glm_saga

Minimal, standalone library for solving GLMs in PyTorch
Python
23
star
31

AdvEx_Tutorial

Jupyter Notebook
14
star
32

rethinking-backdoor-attacks

Python
14
star
33

bias-transfer

Python
13
star
34

robustness_lib

Python
12
star
35

journey-TRAK

Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"
Python
12
star
36

datamodels

Python
12
star
37

rla

Residue Level Alignment
Python
12
star
38

copriors

Combining Diverse Feature Priors
Python
8
star
39

missingness

Code for our ICLR 2022 paper "Missingness Bias in Model Debugging"
Jupyter Notebook
5
star
40

fast_l1

Jupyter Notebook
3
star
41

pytorch-lightning-imagenet

Python
3
star
42

post--adv-discussion

HTML
2
star
43

AIaaS_Supply_Chains

Dataset and overview
2
star
44

pytorch-example-imagenet

Python
1
star
45

robust_model_colab

JavaScript
1
star