FGSM（Fast Gradient Sign Method）算法源码解析

原创

已于 2023-10-31 17:41:27 修改 · 1.1k 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#神经网络 #安全 #人工智能 #算法

于 2023-10-28 11:03:22 首次发布

本文详细介绍了FGSM（FastGradientSignMethod）算法，一种在白盒环境下的无目标和目标攻击方法，通过计算损失函数对输入的梯度进行扰动。它假设目标损失函数与输入之间的关系近似线性，用于生成对抗样本。

论文链接：https://arxiv.org/abs/1412.6572
源码出处：https://github.com/Harry24k/adversarial-attacks-pytorch/tree/master

源码

import torch
import torch.nn as nn

from ..attack import Attack


class FGSM(Attack):
    r"""
    FGSM in the paper 'Explaining and harnessing adversarial examples'
    [https://arxiv.org/abs/1412.6572]

    Distance Measure : Linf

    Arguments:
        model (nn.Module): model to attack.
        eps (float): maximum perturbation. (Default: 8/255)

    Shape:
        - images: :math:`(N, C, H, W)` where `N = number of batches`, `C = number of channels`,        `H = height` and `W = width`. It must have a range [0, 1].
        - labels: :math:`(N)` where each value :math:`y_i` is :math:`0 \leq y_i \leq` `number of labels`.
        - output: :math:`(N, C, H, W)`.

    Examples::
        >>> attack = torchattacks.FGSM(model, eps=8/255)
        >>> adv_images = attack(images, labels)

    """
    def __init__(self, model, eps=8/255):
        super().__init__("FGSM", model)
        self.eps = eps
        self.supported_mode = ['default', 'targeted']

    def forward(self, images, labels):
        r"""
        Overridden.
        """
        self._check_inputs(images)

        images = images.clone().detach().to(self.device)
        labels = labels.clone().detach().to(self.device)

        if self.targeted:
            target_labels = self.get_target_label(images, labels)

        loss = nn.CrossEntropyLoss()

        images.requires_grad = True
        outputs = self.get_logits(images)

        # Calculate loss
        if self.targeted:
            cost = -loss(outputs, target_labels)

最低0.47元/天解锁文章