对抗样本生成

epsilons = [0, .05, .1, .15, .2, .25, .3]
pretrained_model = "data/lenet_mnist_model.pth"
# Set random seed for reproducibility
torch.manual_seed(42)

<torch._C.Generator object at 0x7f3682196390>

# LeNet Model definition
classNet(nn.Module):
    def__init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    defforward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output

# MNIST Test dataset and dataloader declaration
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=False, download=True, transform=transforms.Compose([
            transforms.ToTensor(),
            transforms.Normalize((0.1307,), (0.3081,)),
            ])),
        batch_size=1, shuffle=True)

# We want to be able to train our model on an `accelerator <https://pytorch.org/docs/stable/torch.html#accelerators>`__
# such as CUDA, MPS, MTIA, or XPU. If the current accelerator is available, we will use it. Otherwise, we use the CPU.
device = torch.accelerator.current_accelerator().type if torch.accelerator.is_available() else "cpu"
print(f"Using {device} device")

# Initialize the network
model = Net().to(device)

# Load the pretrained model
model.load_state_dict(torch.load(pretrained_model, map_location=device, weights_only=True))

# Set the model in evaluation mode. In this case this is for the Dropout layers
model.eval()

  0%|          | 0.00/9.91M [00:00<?, ?B/s]
100%|##########| 9.91M/9.91M [00:00<00:00, 149MB/s]

  0%|          | 0.00/28.9k [00:00<?, ?B/s]
100%|##########| 28.9k/28.9k [00:00<00:00, 52.4MB/s]

  0%|          | 0.00/1.65M [00:00<?, ?B/s]
100%|##########| 1.65M/1.65M [00:00<00:00, 166MB/s]

  0%|          | 0.00/4.54k [00:00<?, ?B/s]
100%|##########| 4.54k/4.54k [00:00<00:00, 19.4MB/s]
Using cuda device

Net(
  (conv1): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1))
  (conv2): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1))
  (dropout1): Dropout(p=0.25, inplace=False)
  (dropout2): Dropout(p=0.5, inplace=False)
  (fc1): Linear(in_features=9216, out_features=128, bias=True)
  (fc2): Linear(in_features=128, out_features=10, bias=True)
)

# FGSM attack code
deffgsm_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

# restores the tensors to their original scale
defdenorm(batch, mean=[0.1307], std=[0.3081]):
"""
    Convert a batch of tensors to their original scale.

    Args:
        batch (torch.Tensor): Batch of normalized tensors.
        mean (torch.Tensor or list): Mean used for normalization.
        std (torch.Tensor or list): Standard deviation used for normalization.

    Returns:
        torch.Tensor: batch of tensors without normalization applied to them.
    """
    if isinstance(mean, list):
        mean = torch.tensor(mean).to(device)
    if isinstance(std, list):
        std = torch.tensor(std).to(device)

    return batch * std.view(1, -1, 1, 1) + mean.view(1, -1, 1, 1)

deftest( model, device, test_loader, epsilon ):

    # Accuracy counter
    correct = 0
    adv_examples = []

    # Loop over all examples in test set
    for data, target in test_loader:

        # Send the data and label to the device
        data, target = data.to(device), target.to(device)

        # 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, don't 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

        # Restore the data to its original scale
        data_denorm = denorm(data)

        # Call FGSM Attack
        perturbed_data = fgsm_attack(data_denorm, epsilon, data_grad)

        # Reapply normalization
        perturbed_data_normalized = transforms.Normalize((0.1307,), (0.3081,))(perturbed_data)

        # Re-classify the perturbed image
        output = model(perturbed_data_normalized)

        # 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().cpu().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().cpu().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(f"Epsilon: {epsilon}\tTest Accuracy = {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, device, test_loader, eps)
    accuracies.append(acc)
    examples.append(ex)

Epsilon: 0      Test Accuracy = 9912 / 10000 = 0.9912
Epsilon: 0.05   Test Accuracy = 9605 / 10000 = 0.9605
Epsilon: 0.1    Test Accuracy = 8743 / 10000 = 0.8743
Epsilon: 0.15   Test Accuracy = 7111 / 10000 = 0.7111
Epsilon: 0.2    Test Accuracy = 4877 / 10000 = 0.4877
Epsilon: 0.25   Test Accuracy = 2717 / 10000 = 0.2717
Epsilon: 0.3    Test Accuracy = 1418 / 10000 = 0.1418

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()

# Plot several examples of adversarial samples at each epsilon
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(f"Eps: {epsilons[i]}", fontsize=14)
        orig,adv,ex = examples[i][j]
        plt.title(f"{orig} -> {adv}")
        plt.imshow(ex, cmap="gray")
plt.tight_layout()
plt.show()