为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速览选取了来自南京航空航天大学的模型知识产权保护 (Model IP Protection)的工作。该工作由张道强教授和付华柱研究员指导,论文一作汪恋雨同学录制。 论文题目:Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection 作者列表: 汪恋雨 (南京航空航天大学),王猛 (新加坡科技研究局),张道强 (南京航空航天大学),付华柱 (新加坡科技研究局) B站观看网址: 论文摘要: As scientific and technological advancements result from human intellectual labor and computational costs, protecting model intellectual property (IP) has become increasingly important to encourage model creators and owners, involves preventing the use of well-trained models on unauthorized domains. This talk will present some of our recent work of a novel approach called Compact Un-Transferable Isolation Domain (CUTI-domain), which acts as a barrier to block illegal transfers from authorized to unauthorized domains. Two solutions are designed for using CUTI-domain depending on whether the unauthorized domain is known or not. We will also discuss how CUTI domains facilitate ownership verification and applicability authorization in real-world scenarios. 论文信息: [1] Lianyu Wang, Meng Wang, Daoqiang Zhang, Huazhu Fu, “Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection,” IEEE Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, June 2023. 论文链接: [https://arxiv.org/abs/2303.11078] 视频讲者简介: Lianyu Wang is a first-year PhD at the College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, under the supervision of Prof. Daoqiang Zhang. Her main research directions are domain adaptation and model intellectual property protection. 个人主页: http://ibrain.nuaa.edu.cn/ 特别鸣谢本次论文速览主要组织者: 月度轮值AC:秦杰 (南京航空航天大学) 季度轮值AC:叶茫 (武汉大学) 活动参与方式 1、VALSE每周举行的Webinar活动依托B站直播平台进行,欢迎在B站搜索VALSE_Webinar关注我们! 直播地址: https://live.bilibili.com/22300737; 历史视频观看地址: https://space.bilibili.com/562085182/ 2、VALSE Webinar活动通常每周三晚上20:00进行,但偶尔会因为讲者时区问题略有调整,为方便您参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ S群,群号:317920537); *注:申请加入VALSE QQ群时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。 3、VALSE微信公众号一般会在每周四发布下一周Webinar报告的通知。 4、您也可以通过访问VALSE主页:http://valser.org/ 直接查看Webinar活动信息。Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新。 |
小黑屋|手机版|Archiver|Vision And Learning SEminar
GMT+8, 2024-12-26 20:46 , Processed in 0.012859 second(s), 14 queries .
Powered by Discuz! X3.4
Copyright © 2001-2020, Tencent Cloud.