Disrupting Diffusion-based Inpainters with Semantic Digression

TL;DR

This paper introduces DDD, a semantic digression-based framework that significantly improves the disruption of diffusion-based inpainting models, making it more effective, faster, and resource-efficient than previous methods like Photoguard.

Contribution

The paper proposes DDD, a novel semantic digression approach that enhances inpainting disruption by identifying vulnerable diffusion timesteps and optimizing hidden state distances.

Findings

DDD achieves higher disruption success rates than Photoguard.

It reduces GPU memory requirements and speeds up the disruption process.

The method effectively targets the most vulnerable diffusion timesteps for disruption.

Abstract

The fabrication of visual misinformation on the web and social media has increased exponentially with the advent of foundational text-to-image diffusion models. Namely, Stable Diffusion inpainters allow the synthesis of maliciously inpainted images of personal and private figures, and copyrighted contents, also known as deepfakes. To combat such generations, a disruption framework, namely Photoguard, has been proposed, where it adds adversarial noise to the context image to disrupt their inpainting synthesis. While their framework suggested a diffusion-friendly approach, the disruption is not sufficiently strong and it requires a significant amount of GPU and time to immunize the context image. In our work, we re-examine both the minimal and favorable conditions for a successful inpainting disruption, proposing DDD, a "Digression guided Diffusion Disruption" framework. First, we identify the most adversarially vulnerable diffusion timestep range with respect to the hidden space. Within this scope of noised manifold, we pose the problem as a semantic digression optimization. We maximize the distance between the inpainting instance's hidden states and a semantic-aware hidden state centroid, calibrated both by Monte Carlo sampling of hidden states and a discretely projected optimization in the token space. Effectively, our approach achieves stronger disruption and a higher success rate than Photoguard while lowering the GPU memory requirement, and speeding the optimization up to three times faster.