Dormant: Defending against Pose-driven Human Image Animation

TL;DR

Dormant is a protection method that applies subtle perturbations to images to prevent pose-driven human image animation, maintaining visual similarity while causing generated videos to be incoherent and distorted.

Contribution

We introduce Dormant, a novel image perturbation technique that effectively defends against pose-driven animation methods, outperforming existing protection approaches.

Findings

Dormant causes misaligned identities in generated videos.

It introduces visual distortions and artifacts.

Effective even in black-box scenarios.

Abstract

Pose-driven human image animation has achieved tremendous progress, enabling the generation of vivid and realistic human videos from just one single photo. However, it conversely exacerbates the risk of image misuse, as attackers may use one available image to create videos involving politics, violence, and other illegal content. To counter this threat, we propose Dormant, a novel protection approach tailored to defend against pose-driven human image animation techniques. Dormant applies protective perturbation to one human image, preserving the visual similarity to the original but resulting in poor-quality video generation. The protective perturbation is optimized to induce misextraction of appearance features from the image and create incoherence among the generated video frames. Our extensive evaluation across 8 animation methods and 4 datasets demonstrates the superiority of Dormant over 6 baseline protection methods, leading to misaligned identities, visual distortions, noticeable artifacts, and inconsistent frames in the generated videos. Moreover, Dormant shows effectiveness on 6 real-world commercial services, even with fully black-box access.