High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis

Takuto Onikubo, Yusuke Matsui

Keywords: Fake Image, Image Generative Model, Adversarial Attack

TL;DR: We have proposed a more robust adversarial attack method against fake image generation.

Abstract: Recently, text-to-image generative models have been misused to create unauthorized malicious images of individuals, posing a growing social problem. Previous solutions, such as Anti-DreamBooth, add adversarial noise to images to protect them from being used as training data for malicious generation. However, we found that the adversarial noise can be removed by adversarial purification methods such as DiffPure. Therefore, we propose a new adversarial attack method that adds strong perturbation on the high-frequency areas of images to make it more robust to adversarial purification. Our experiment showed that the adversarial images retained noise even after adversarial purification, hindering malicious image generation.

Submission Number: 3