Anti-I2V: Safeguarding your photos from malicious image-to-video generation

TL;DR

This paper introduces Anti-I2V, a novel defense method that protects images from malicious diffusion-based video generation by operating in multiple domains and targeting key network features, achieving state-of-the-art robustness.

Contribution

Anti-I2V is a new defense approach that works across various diffusion models, including DiT, by operating in both color and frequency domains and focusing on semantic features during denoising.

Findings

Anti-I2V outperforms existing defenses against multiple diffusion models.

It effectively degrades temporal coherence and generation fidelity.

The method is applicable across diverse diffusion backbones.

Abstract

Advances in diffusion-based video generation models, while significantly improving human animation, poses threats of misuse through the creation of fake videos from a specific person's photo and text prompts. Recent efforts have focused on adversarial attacks that introduce crafted perturbations to protect images from diffusion-based models. However, most existing approaches target image generation, while relatively few explicitly address image-to-video diffusion models (VDMs), and most primarily focus on UNet-based architectures. Hence, their effectiveness against Diffusion Transformer (DiT) models remains largely under-explored, as these models demonstrate improved feature retention, and stronger temporal consistency due to larger capacity and advanced attention mechanisms. In this work, we introduce Anti-I2V, a novel defense against malicious human image-to-video generation, applicable across diverse diffusion backbones. Instead of restricting noise updates to the RGB space, Anti-I2V operates in both the $L$*$a$*$b$* and frequency domains, improving robustness and concentrating on salient pixels. We then identify the network layers that capture the most distinct semantic features during the denoising process to design appropriate training objectives that maximize degradation of temporal coherence and generation fidelity. Through extensive validation, Anti-I2V demonstrates state-of-the-art defense performance against diverse video diffusion models, offering an effective solution to the problem.