High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913570166407168 |
|---|---|
| author | Onikubo, Takuto Matsui, Yusuke |
| author_facet | Onikubo, Takuto Matsui, Yusuke |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08167 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis Onikubo, Takuto Matsui, Yusuke Computer Vision and Pattern Recognition 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. |
| title | High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.08167 |