Quan Yuan (Zhejiang University), Zhikun Zhang (Zhejiang University), Linkang Du (Xi'an Jiaotong University), Min Chen (Vrije Universiteit Amsterdam), Mingyang Sun (Peking University), Yunjun Gao (Zhejiang University), Shibo He (Zhejiang University), Jiming Chen (Zhejiang University and Hangzhou Dianzi University)

Video recognition systems are increasingly being deployed in daily life, such as content recommendation and security monitoring. To enhance video recognition development, many institutions have released high-quality public datasets with open-source licenses for training advanced models. At the same time, these datasets are also susceptible to misuse and infringement. Dataset copyright auditing is an effective solution to identify such unauthorized use. However, existing dataset copyright solutions primarily focus on the image domain; the complex nature of video data leaves dataset copyright auditing in the video domain unexplored. Specifically, video data introduces an additional temporal dimension, which poses significant challenges to the effectiveness and stealthiness of existing methods.

In this paper, we propose VICTOR, the first dataset copyright auditing approach for video recognition systems. We develop a general and stealthy sample modification strategy that enhances the output discrepancy of the target model. By modifying only a small proportion of samples (e.g., 1%), VICTOR amplifies the impact of published modified samples on the prediction behavior of the target models. Then, the difference in the model’s behavior for published modified and unpublished original samples can serve as a key basis for dataset auditing. Extensive experiments on multiple models and datasets highlight the superiority of VICTOR. Finally, we show that VICTOR is robust in the presence of several perturbation mechanisms to the training videos or the target models.

View More Papers

Revealing The Secret Power: How Algorithms Can Influence Content...

Alessandro Galeazzi (University of Padua), Pujan Paudel (Boston University), Mauro Conti (University of Padua and Orebro University), Emiliano De Cristofaro (University of California, Riverside), Gianluca Stringhini (Boston University)

Read More

Targeted Physical Evasion Attacks in the Near-Infrared Domain

Pascal Zimmer (Ruhr University Bochum), Simon Lachnit (Ruhr University Bochum), Alexander Jan Zielinski (Ruhr University Bochum), Ghassan Karame (Ruhr University Bochum)

Read More

What Do They Fix? LLM-Aided Categorization of Security Patches...

Xingyu Li (UC Riverside), Juefei Pu (UC Riverside), Yifan Wu (UC Riverside), Xiaochen Zou (UC Riverside), Shitong Zhu (UC Riverside), Qiushi Wu (IBM), Zheng Zhang (UC Riverside), Joshua Hsu (UC Riverside), Yue Dong (UC Riverside), Zhiyun Qian (UC Riverside), Kangjie Lu (University of Minnesota), Trent Jaeger (UC Riverside), Michael De Lucia (U.S. Army Research Laboratory),…

Read More