+高级检索
基于图像去噪和图像生成的对抗样本检测方法
DOI:
作者:
作者单位:

作者简介:

通讯作者:

基金项目:


Adversarial Example Detection Method Based on Image Denoising and Image Generation
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    针对现有对抗样本检测方法存在检测准确率低和训练收敛速度慢等问题,提出一种基于图像去噪技术和图像生成技术实现的对抗样本检测方法.该检测方法将对抗样本检测问题转换为图像分类问题,无须事先得知被攻击模型的结构和参数,仅使用图像的语义信息和分类标签信息即可判定图像是否为对抗样本.首先,采用基于swin-transformer和vision-transformer实现的移动窗口式掩码自编码器去除图像中的对抗性噪声,还原图像的语义信息.然后,使用基于带有梯度惩罚的条件生成式对抗网络实现的图像生成部分根据图像分类标签信息生成图像.最后,将前两阶段输出的图像输入卷积神经网络进行分类,通过对比完成去噪的图像和生成图像的分类结果一致性判定检测图像是否为对抗样本.在MNIST、GTSRB和CIAFAR-10数据集上的实验结果表明,相比于传统检测方法,本文提出的对抗样本检测方法的平均检测准确率提高6%~36%,F1分数提高6%~37%,训练收敛耗时缩减27%~83%,存在一定优势.

    Abstract:

    In order to solve the problems of low detection accuracy, slow training convergence speed of existing adversarial example detection methods, a method of adversarial example detection based on image denoising technology and image generation technology is proposed. The detection method converts the adversarial example detection problem into an image classification problem. It does not need to know the structure and parameters of the attacked model in advance, and only uses the semantic information and classification label information of the image to determine whether the image is an adversarial example. Firstly, a shifted masked auto-encoder based on swin-transformer and vision-transformer is used to remove the adversarial noise in the image and restore the semantic information of the image. Then, the image generation part based on conditional generative adversarial networks with gradient penalty is used to generate images based on image classification label information. Finally, the output of the images in the first two stages is input into the convolutional neural network for classification. By comparing the classification results of the denoised images and the generated images, it is determined whether the detected images are adversarial examples. The experimental results on MNIST, GTSRB, and CIAFAR-10 datasets show that the proposed adversarial example detection method outperforms the traditional detection methods. The average detection accuracy of this method is improved by 6%~36%, the F1 score is increased by 6%~37%, and the training convergence time is reduced by 27%~83%, respectively.

    参考文献
    相似文献
    引证文献
文章指标
  • PDF下载次数:
  • HTML阅读次数:
  • 摘要点击次数:
  • 引用次数:
引用本文

杨宏宇 ?,杨帆 .基于图像去噪和图像生成的对抗样本检测方法[J].湖南大学学报:自然科学版,2023,(8):72~81

复制
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2023-08-29
  • 出版日期:
作者稿件一经被我刊录用,如无特别声明,即视作同意授予我刊论文整体的全部复制传播的权利,包括但不限于复制权、发行权、信息网络传播权、广播权、表演权、翻译权、汇编权、改编权等著作使用权转让给我刊,我刊有权根据工作需要,允许合作的数据库、新媒体平台及其他数字平台进行数字传播和国际传播等。特此声明。
关闭