Tools for Robustness
Project description
robustness is a package we (students in the MadryLab) created to make training, evaluating, and exploring neural networks flexible and easy. We use it in almost all of our projects (whether they involve adversarial training or not!) and it will be a dependency in many of our upcoming code releases. A few projects using the library include:
Code for “Learning Perceptually-Aligned Representations via Adversarial Robustness” (https://arxiv.org/abs/1906.00945)
Code for “Image Synthesis with a Single (Robust) Classifier” (https://arxiv.org/abs/1906.09453)
(Have you used the package and found it useful? Let us know!). We demonstrate how to use the library in a set of walkthroughs and our API reference. Functionality provided by the library includes:
Training and evaluating standard and robust models for a variety of datasets/architectures using a CLI interface. The library also provides support for adding custom datasets and model architectures.
python -m robustness.main --dataset cifar --data /path/to/cifar \
--adv-train 0 --arch resnet18 --out-dir /logs/checkpoints/dir/
Performing input manipulation using robust (or standard) models—this includes making adversarial examples, inverting representations, feature visualization, etc. The library offers a variety of optimization options (e.g. choice between real/estimated gradients, Fourier/pixel basis, custom loss functions etc.), and is easily extendable.
import torch as ch
from robustness.datasets import CIFAR
from robustness.model_utils import make_and_restore_model
ds = CIFAR('/path/to/cifar')
model, _ = make_and_restore_model(arch='resnet50', dataset=ds,
resume_path='/path/to/model', state_dict_path='model')
model.eval()
attack_kwargs = {
'constraint': 'inf', # L-inf PGD
'eps': 0.05, # Epsilon constraint (L-inf norm)
'step_size': 0.01, # Learning rate for PGD
'iterations': 100, # Number of PGD steps
'targeted': True # Targeted attack
'custom_loss': None # Use default cross-entropy loss
}
_, test_loader = ds.make_loaders(workers=0, batch_size=10)
im, label = next(iter(test_loader))
target_label = (label + ch.randint_like(label, high=9)) % 10
adv_out, adv_im = model(im, target_label, make_adv, **attack_kwargs)
Importing robustness as a package, which allows for easy training of neural networks with support for custom loss functions, logging, data loading, and more! A good introduction can be found in our two-part walkthrough (Part 1, Part 2).
from robustness import model_utils, datasets, train, defaults
from robustness.datasets import CIFAR
# We use cox (http://github.com/MadryLab/cox) to log, store and analyze
# results. Read more at https//cox.readthedocs.io.
from cox.utils import Parameters
import cox.store
# Hard-coded dataset, architecture, batch size, workers
ds = CIFAR('/path/to/cifar')
m, _ = model_utils.make_and_restore_model(arch='resnet50', dataset=ds)
train_loader, val_loader = ds.make_loaders(batch_size=128, workers=8)
# Create a cox store for logging
out_store = cox.store.Store(OUT_DIR)
# Hard-coded base parameters
train_kwargs = {
'out_dir': "train_out",
'adv_train': 1,
'constraint': '2',
'eps': 0.5,
'attack_lr': 1.5,
'attack_steps': 20
}
train_args = Parameters(train_kwargs)
# Fill whatever parameters are missing from the defaults
train_args = defaults.check_and_fill_args(train_args,
defaults.TRAINING_ARGS, CIFAR)
train_args = defaults.check_and_fill_args(train_args,
defaults.PGD_ARGS, CIFAR)
# Train a model
train.train_model(train_args, m, (train_loader, val_loader), store=out_store)
Citation
If you use this library in your research, cite it as follows:
@misc{robustness,
title={Robustness},
author={},
year={2019},
url={git.io/robustness-lib}
}
Documentation
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.