MadryLab/pytorch-lightning-imagenet

Stars
3
Rank 3,963,521 (Top 79 %)
Language
Python
License
Apache License 2.0
Created about 3 years ago
Updated almost 2 years ago

MadryLab/pytorch-lightning-imagenet

MadryLab

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

robustness

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

Jupyter Notebook

mnist_challenge

A challenge to explore adversarial robustness of neural networks on MNIST.

cifar10_challenge

A challenge to explore adversarial robustness of neural networks on CIFAR10.

photoguard

Raising the Cost of Malicious AI-Powered Image Editing

Jupyter Notebook

constructed-datasets

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

trak

A fast, effective data attribution method for neural networks in PyTorch

robust_representations

Code for "Learning Perceptually-Aligned Representations via Adversarial Robustness"

Jupyter Notebook

backgrounds_challenge

robustness_applications

Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"

Jupyter Notebook

implementation-matters

EditingClassifiers

robust-features-code

Code for "Robustness May Be at Odds with Accuracy"

Jupyter Notebook

datamodels-data

Data for "Datamodels: Predicting Predictions with Training Data"

blackbox-bandits

Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"

BREEDS-Benchmarks

Jupyter Notebook

cox

A lightweight experimental logging library

adversarial_spatial

Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.

modeldiff

ModelDiff: A Framework for Comparing Learning Algorithms

Jupyter Notebook

failure-directions

Distilling Model Failures as Directions in Latent Space

Jupyter Notebook

smoothed-vit

Certified Patch Robustness via Smoothed Vision Transformers

label-consistent-backdoor-code

Code for "Label-Consistent Backdoor Attacks"

dataset-interfaces

Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation

Jupyter Notebook

DebuggableDeepNetworks

Jupyter Notebook

data-transfer

ImageNetMultiLabel

Fine-grained ImageNet annotations

Jupyter Notebook

relu_stable

spatial-pytorch

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

Jupyter Notebook

dataset-replication-analysis

Jupyter Notebook

backdoor_data_poisoning

glm_saga

Minimal, standalone library for solving GLMs in PyTorch

AdvEx_Tutorial

Jupyter Notebook

rethinking-backdoor-attacks

bias-transfer

robustness_lib

journey-TRAK

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

datamodels

rla

Residue Level Alignment

copriors

Combining Diverse Feature Priors

missingness

Code for our ICLR 2022 paper "Missingness Bias in Model Debugging"

Jupyter Notebook

fast_l1

Jupyter Notebook

post--adv-discussion

AIaaS_Supply_Chains

Dataset and overview

pytorch-example-imagenet

mnist_challenge_models

robust_model_colab