Validation on adversarial samples for OOD detection

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

This project is for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks". Some codes are from odin-pytorch, LID, and adversarial_image_defenses.

Preliminaries

It is tested under Ubuntu Linux 16.04.1 and Python 3.6 environment, and requries Pytorch package to be installed:

Pytorch: Only GPU version is available.
scipy
scikit-learn

Downloading Out-of-Distribtion Datasets

We use download links of two out-of-distributin datasets from odin-pytorch:

Please place them to ./data/.

Downloading Pre-trained Models

We provide six pre-trained neural networks (1) three DenseNets trained on CIFAR-10, CIFAR-100 and SVHN, where models trained on CIFAR-10 and CIFAR-100 are from odin-pytorch, and (2) three ResNets trained on CIFAR-10, CIFAR-100 and SVHN.

Please place them to ./pre_trained/.

Detecting Out-of-Distribution Samples (Baseline and ODIN)

# model: ResNet, in-distribution: CIFAR-10, gpu: 0
python OOD_Baseline_and_ODIN.py --dataset cifar10 --net_type resnet --gpu 0

Detecting Out-of-Distribution Samples (Mahalanobis detector)

1. Extract detection characteristics:

# model: ResNet, in-distribution: CIFAR-10, gpu: 0
python OOD_Generate_Mahalanobis.py --dataset cifar10 --net_type resnet --gpu 0

2. Train simple detectors:

# model: ResNet
python OOD_Regression_Mahalanobis.py --net_type resnet

Detecting Adversarial Samples (LID & Mahalanobis detector)

0. Generate adversarial samples:

# model: ResNet, in-distribution: CIFAR-10, adversarial attack: FGSM  gpu: 0
python ADV_Samples.py --dataset cifar10 --net_type resnet --adv_type FGSM --gpu 0

1. Extract detection characteristics:

# model: ResNet, in-distribution: CIFAR-10, adversarial attack: FGSM  gpu: 0
python ADV_Generate_LID_Mahalanobis.py --dataset cifar10 --net_type resnet --adv_type FGSM --gpu 0

2. Train simple detectors:

# model: ResNet
python ADV_Regression.py --net_type resnet

	precision = []
	for k in range(num_output):
	X = 0
	for i in range(num_classes):
	if i == 0:
	X = list_features[k][i] - sample_class_mean[k][i]
	else:
	X = torch.cat((X, list_features[k][i] - sample_class_mean[k][i]), 0)

	# find inverse
	group_lasso.fit(X.cpu().numpy())
	temp_precision = group_lasso.precision_
	temp_precision = torch.from_numpy(temp_precision).float().cuda()
	precision.append(temp_precision)

pokaxpoka / deep_mahalanobis_detector Goto Github PK

deep_mahalanobis_detector's Introduction

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Preliminaries

Downloading Out-of-Distribtion Datasets

Downloading Pre-trained Models

Detecting Out-of-Distribution Samples (Baseline and ODIN)

Detecting Out-of-Distribution Samples (Mahalanobis detector)

1. Extract detection characteristics:

2. Train simple detectors:

Detecting Adversarial Samples (LID & Mahalanobis detector)

0. Generate adversarial samples:

1. Extract detection characteristics:

2. Train simple detectors:

deep_mahalanobis_detector's People

Contributors

Stargazers

Watchers

Forkers

deep_mahalanobis_detector's Issues

Recommend Projects

Recommend Topics

Recommend Org