无法使用训练有素的 NSGA-Net PyTorch 模型生成对抗性示例

Question

我使用 NSGA-Net 神经架构搜索来生成和训练多个架构。我正在尝试使用经过训练的 PyTorch 模型生成 PGD 对抗样本。我尝试同时使用 Adversarial Robustness Toolbox 1.3 (ART) 和 torchattacks 2.4，但我得到了同样的错误。

这几行代码描述了我的代码的主要功能以及我在这里要实现的目标：

# net is my trained NSGA-Net PyTorch model

# Defining PGA attack

pgd_attack = PGD(net, eps=4 / 255, alpha=2 / 255, steps=3)

# Creating adversarial examples using validation data and the defined PGD attack

for images, labels in valid_data:
    images = pgd_attack(images, labels).cuda()
    outputs = net(images)

所以错误通常是这样的：

Traceback (most recent call last):
  File "torch-attacks.py", line 296, in <module>
    main()
  File "torch-attacks.py", line 254, in main
    images = pgd_attack(images, labels).cuda()
  File "\Anaconda3\envs\GPU\lib\site-packages\torchattacks\attack.py", line 114, in __call__
    images = self.forward(*input, **kwargs)
  File "\Anaconda3\envs\GPU\lib\site-packages\torchattacks\attacks\pgd.py", line 57, in forward
    outputs = self.model(adv_images)
  File "\envs\GPU\lib\site-packages\torch\nn\modules\module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "\codes\NSGA\nsga-net\models\macro_models.py", line 79, in forward
    x = self.gap(self.model(x))
  File "\Anaconda3\envs\GPU\lib\site-packages\torch\nn\modules\module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "\Anaconda3\envs\GPU\lib\site-packages\torch\nn\modules\container.py", line 100, in forward
    input = module(input)
  File "\Anaconda3\envs\GPU\lib\site-packages\torch\nn\modules\module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "\codes\NSGA\nsga-net\models\macro_decoder.py", line 978, in forward
    x = self.first_conv(x)
  File "\Anaconda3\envs\GPU\lib\site-packages\torch\nn\modules\module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "\Anaconda3\envs\GPU\lib\site-packages\torch\nn\modules\conv.py", line 345, in forward
    return self.conv2d_forward(input, self.weight)
  File "\Anaconda3\envs\GPU\lib\site-packages\torch\nn\modules\conv.py", line 342, in conv2d_forward
    self.padding, self.dilation, self.groups)
RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #2 'weight' in call to _thnn_conv2d_forward

我在一个简单的 PyTorch 模型中使用了相同的代码并且它有效，但我使用的是 NSGA-Net，所以我没有自己设计模型。我也尝试在模型和输入上使用 .float()，但仍然出现相同的错误。

请记住，我只能访问以下文件：

手电筒-attacks.py
macro_models.py
macro_decoder.py

Answer 1

您应该将 images 转换为所需的类型（在您的情况下为 images.float()）。标签必须不能转换为任何浮动类型。它们可以是 int 或 long 张量。

无法使用训练有素的 NSGA-Net PyTorch 模型生成对抗性示例

Failed to generate adversarial examples using trained NSGA-Net PyTorch models

python

robustness

neural-network

python-3.x

pytorch