FIVA: Facial Image and Video Anonymization and Anonymization Defense
This work addresses privacy and security issues in facial data for applications like surveillance and media, though it appears incremental by building on existing anonymization and defense techniques.
The paper tackles the problem of facial anonymization in images and videos by proposing FIVA, a method that maintains consistent anonymization across frames and ensures strong differences from original faces, achieving 0 true positives at a false acceptance rate of 0.001. It also explores defense against reconstruction attacks and demonstrates applications in deep fake detection and face swapping trained on a single target image.
In this paper, we present a new approach for facial anonymization in images and videos, abbreviated as FIVA. Our proposed method is able to maintain the same face anonymization consistently over frames with our suggested identity-tracking and guarantees a strong difference from the original face. FIVA allows for 0 true positives for a false acceptance rate of 0.001. Our work considers the important security issue of reconstruction attacks and investigates adversarial noise, uniform noise, and parameter noise to disrupt reconstruction attacks. In this regard, we apply different defense and protection methods against these privacy threats to demonstrate the scalability of FIVA. On top of this, we also show that reconstruction attack models can be used for detection of deep fakes. Last but not least, we provide experimental results showing how FIVA can even enable face swapping, which is purely trained on a single target image.