ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
会议论文

NEURAL NETWORK FRAGILE WATERMARKING WITH NO MODEL PERFORMANCE DEGRADATION

Yin, Zhaoxia*; Yin, Heng; Zhang, Xinpeng复旦大学
IEEE International Conference on Image Processing (ICIP)2022DOI: 10.1109/ICIP46576.2022.9897413
4被引6阅读
引用收藏
分享

摘要

Deep neural networks are vulnerable to malicious fine-tuning attacks such as data poisoning and backdoor attacks. Therefore, in recent research, it is proposed how to detect malicious fine-tuning of neural network models. However, it usually negatively affects the performance of the protected model. Thus, we propose a novel neural network fragile watermarking with no model performance degradation. In the process of watermarking, we train a generative model with the specific loss function and secret key to generate triggers that are sensitive to the fine-tuning of the target classifier. In the process of verifying, we adopt the watermarked classifier to get labels of each fragile trigger. Then, malicious fine-tuning can be detected by comparing secret keys and labels. Experiments on classic datasets and classifiers show that the proposed method can effectively detect model malicious fine-tuning with no model performance degradation.

学科与关键词

关键词
Neural networkFragile watermarkingModel integrity protectionMalicious tuning detectionBackdoor attack
相关
加载中…

文献加载失败,请重试

重试

会议信息

会议名称
IEEE International Conference on Image Processing (ICIP)
会议日期
2022-10-16 至 2022-10-19
论文集名
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP
发表日期
2022
起止页码
3958-3962
DOI
10.1109/ICIP46576.2022.9897413
资助标注
National Natural Science Foundation of China [62172001, U1936214]
收录
ISTP

作者

  • Y

    Yin, Zhaoxia (通讯) (第一作者)

  • Y

    Yin, Heng

    anhui univ

查看全部 3 位作者收起作者
  • Z

    Zhang, Xinpeng

    fudan univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417