面向卷积神经网络泛化性和健壮性权衡的标签筛选方法
CSTR:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP18

基金项目:

国家自然科学基金(62371254, 61906098)


Label Screening Method for Generalization and Robustness Trade-off in Convolutional Neural Network
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
  • |
  • 文章评论
    摘要:

    虽然卷积神经网络凭借优异的泛化性能被广泛应用在图像识别领域中, 但被噪声污染的对抗样本可以轻松欺骗训练完全的网络模型, 带来安全性的隐患. 现有的许多防御方法虽然提高了模型的健壮性, 但大多数不可避免地牺牲了模型的泛化性. 为了缓解这一问题, 提出了标签筛选权重参数正则化方法, 在模型训练过程中利用样本的标签信息权衡模型的泛化性和健壮性. 先前的许多健壮模型训练方法存在下面两个问题: 1)大多通过增加训练集样本的数量或复杂度来提高模型的健壮性, 这不仅弱化了干净样本在模型训练过程中的主导作用, 也使得训练任务的工作量大大提高; 2)样本的标签信息除了被用于与模型预测结果对比来控制模型参数的更新方向以外, 在模型训练中几乎不被另作使用, 这无疑忽视了隐藏于样本标签中的更多信息. 所提方法通过样本的正确标签和对抗样本的分类标签筛选出模型在分类该样本时起决定性作用的权重参数, 对这些参数进行正则优化, 达到模型泛化性和健壮性权衡的效果. 在MNIST、CIFAR-10和CIFAR-100数据集上的实验和分析表明, 提出的方法能够取得很好的训练效果.

    Abstract:

    Although convolutional neural networks (CNNs) are widely used in image recognition due to their excellent generalization performance, adversarial samples contaminated by noise can easily deceive fully trained network models, posing security risks. Many existing defense methods improve the robustness of models, but most inevitably sacrifice model generalization. To alleviate this issue, a label-filtered weight parameter regularization method is proposed to balance the generalization and robustness of models using the label information of samples during model training. Many previous robust model training methods suffer from two main issues: 1) The robustness of models is mainly enhanced by increasing the quantity or complexity of training set samples, which not only diminishes the dominant role of clean samples in model training but also significantly increases the workload of training tasks. 2) The label information of samples is used only to compare with model predictions to control the direction of model parameter updates, neglecting the additional information hidden in sample labels. The proposed method selects weight parameters that play a decisive role in classifying samples by filtering the correct labels of samples and the classification labels of adversarial samples and optimizes these parameters regularly to achieve a balance between model generalization and robustness. Experiments and analysis on the MNIST, CIFAR-10, and CIFAR-100 datasets demonstrate that the proposed method achieves good training results.

    参考文献
    相似文献
    引证文献
引用本文

王益民,龙显忠,李云,熊健.面向卷积神经网络泛化性和健壮性权衡的标签筛选方法.软件学报,,():1-16

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-11-07
  • 最后修改日期:2023-12-24
  • 录用日期:
  • 在线发布日期: 2024-06-14
  • 出版日期:
文章二维码
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号