Universal Adversarial Head: Practical Protection against Video Data Leakage

Jiawang Bai, Bin Chen, Dongxian Wu, Chaoning Zhang, Shu-Tao Xia

Keywords: privacy protection, video retrieval, adversarial attack

TL;DR: We introduce a practical method and extend it to the data-free scenarios to protect the privacy information for the video data.

Abstract: While online video sharing becomes more popular, it also causes unconscious leakage of personal information in the video retrieval systems like deep hashing. An adversary can collect users' private information from the video database by querying similar videos. This paper focuses on bypassing the deep video hashing based retrieval to prevent information from being maliciously collected. We propose $universal \ adversarial \ head$ (UAH), which crafts adversarial query videos by prepending the original videos with a sequence of adversarial frames to perturb the normal hash codes in the Hamming space. This adversarial head can be obtained just using a few videos, and mislead the retrieval system to return irrelevant videos on most natural query videos. Furthermore, to obey the principle of information protection, we expand the proposed method to a data-free paradigm to generate the UAH, without access to users' original videos. Extensive experiments demonstrate the protection effectiveness of our method under various settings.