VICTOR: Dataset Copyright Auditing in Video Recognition Systems
Quan Yuan
Network and Distributed System Security (NDSS) Symposium 2026 · Day 3 · Web Security
As video recognition systems become integral to **autonomous driving**, **security surveillance**, and **healthcare monitoring**, the datasets used to train these models have become valuable intellectual property. Many high-quality video datasets are published under strict open-source licenses that prohibit unauthorized commercial use, yet detecting violations is extremely difficult. This talk introduces **VICTOR**, the first dataset copyright auditing approach specifically designed for video recognition systems. By amplifying behavioral differences between modified and original samples, VICTOR enables dataset owners to detect unauthorized use of their data in third-party models with high accuracy and robustness, even under adversarial evasion attempts.
AI review
A dataset copyright auditing method for video recognition that amplifies behavioral differences to detect unauthorized model training. Technically competent but addresses an IP protection problem rather than a security exploitation or defense challenge, with limited relevance to offensive security practitioners.