''' 但是,设计和训练模型的一个经常被忽略的方面是安全性和鲁棒性,
尤其是在面对想要欺骗模型的对手的情况下
这篇文章的思路就是给图像加噪音,但是大家会发现一件事,加噪音我们希望给神经网络认为重要的像素点给予更多的攻击,
作者的思路是认为,根据梯度来反馈的到大小来反推像素点的重要性,一般来说能使神经网络获得很大梯度的像素点肯定是
重要的。
'''
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import numpy as np
import matplotlib.pyplot as plt
epsilons = [0, .05, .1, .15, .2, .25, .3]
pretrained_model = "lenet_mnist_model.pth"
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
# MNIST Test dataset and dataloader declaration
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False, download=True, transform=transforms.Compose([
transforms.ToTensor(),
])),
batch_size=1, shuffle=True)
model = Net()
# Load the pretrained model
model.load_state_dict(torch.load(pretrained_model, map_location='cpu'))
# Set the model in evaluation mode. In this case this is for the Dropout layers
model.eval()
def fgsm_attack(image, epsilon, data_grad):
# Collect the element-wise sign of the data gradient
sign_data_grad = data_grad.sign()
# Create the perturbed image by adjusting each pixel of the input image
perturbed_image = image + epsilon*sign_data_grad
# Adding clipping to maintain [0,1] range
perturbed_image = torch.clamp(perturbed_image, 0, 1)
# Return the perturbed image
return perturbed_image
def test(model, test_loader, epsilon):
# Accuracy counter
correct = 0
adv_examples = []
# Loop over all examples in test set
for data, target in test_loader:
# Set requires_grad attribute of tensor. Important for Attack
data.requires_grad = True
# Forward pass the data through the model
output = model(data)
init_pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
# If the initial prediction is wrong, dont bother attacking, just move on
if init_pred.item() != target.item():
continue
# Calculate the loss
loss = F.nll_loss(output, target)
# Zero all existing gradients
model.zero_grad()
# Calculate gradients of model in backward pass
loss.backward()
# Collect datagrad
data_grad = data.grad.data
# Call FGSM Attack
perturbed_data = fgsm_attack(data, epsilon, data_grad)
# Re-classify the perturbed image
output = model(perturbed_data)
# Check for success
final_pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
if final_pred.item() == target.item():
correct += 1
# Special case for saving 0 epsilon examples
if (epsilon == 0) and (len(adv_examples) < 5):
adv_ex = perturbed_data.squeeze().detach().numpy()
adv_examples.append( (init_pred.item(), final_pred.item(), adv_ex) )
else:
# Save some adv examples for visualization later
if len(adv_examples) < 5:
adv_ex = perturbed_data.squeeze().detach().numpy()
adv_examples.append( (init_pred.item(), final_pred.item(), adv_ex) )
# Calculate final accuracy for this epsilon
final_acc = correct/float(len(test_loader))
print("Epsilon: {}\tTest Accuracy = {} / {} = {}".format(epsilon, correct, len(test_loader), final_acc))
# Return the accuracy and an adversarial example
return final_acc, adv_examples
accuracies = []
examples = []
# Run test for each epsilon
for eps in epsilons:
acc, ex = test(model, test_loader, eps)
accuracies.append(acc)
examples.append(ex)
plt.figure(figsize=(5,5))
plt.plot(epsilons, accuracies, "*-")
plt.yticks(np.arange(0, 1.1, step=0.1))
plt.xticks(np.arange(0, .35, step=0.05))
plt.title("Accuracy vs Epsilon")
plt.xlabel("Epsilon")
plt.ylabel("Accuracy")
plt.show()
cnt = 0
plt.figure(figsize=(8,10))
for i in range(len(epsilons)):
for j in range(len(examples[i])):
cnt += 1
plt.subplot(len(epsilons),len(examples[0]),cnt)
plt.xticks([], [])
plt.yticks([], [])
if j == 0:
plt.ylabel("Eps: {}".format(epsilons[i]), fontsize=14)
orig,adv,ex = examples[i][j]
plt.title("{} -> {}".format(orig, adv))
plt.imshow(ex, cmap="gray")
plt.tight_layout()
plt.show()