FIVA: Facial Image and Video Anonymization and Anonymization Defense

TL;DR

FIVA is a novel facial anonymization method for images and videos that maintains consistent anonymization, defends against reconstruction attacks, and can facilitate face swapping using minimal data.

Contribution

The paper introduces FIVA, a new face anonymization technique that ensures consistent anonymization, incorporates defenses against reconstruction attacks, and enables face swapping with limited data.

Findings

FIVA achieves 0 true positives at a 0.001 false acceptance rate.

Defense methods effectively disrupt reconstruction attacks.

FIVA enables face swapping trained on a single image.

Abstract

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.