Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability
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_ | 1866911758167310336 |
|---|---|
| author | Chen, Junxi Dong, Junhao Xie, Xiaohua |
| author_facet | Chen, Junxi Dong, Junhao Xie, Xiaohua |
| contents | Recently, many studies utilized adversarial examples (AEs) to raise the cost of malicious image editing and copyright violation powered by latent diffusion models (LDMs). Despite their successes, a few have studied the surrogate model they used to generate AEs. In this paper, from the perspective of adversarial transferability, we investigate how the surrogate model's property influences the performance of AEs for LDMs. Specifically, we view the time-step sampling in the Monte-Carlo-based (MC-based) adversarial attack as selecting surrogate models. We find that the smoothness of surrogate models at different time steps differs, and we substantially improve the performance of the MC-based AEs by selecting smoother surrogate models. In the light of the theoretical framework on adversarial transferability in image classification, we also conduct a theoretical analysis to explain why smooth surrogate models can also boost AEs for LDMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07087 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability Chen, Junxi Dong, Junhao Xie, Xiaohua Computer Vision and Pattern Recognition Cryptography and Security Machine Learning Recently, many studies utilized adversarial examples (AEs) to raise the cost of malicious image editing and copyright violation powered by latent diffusion models (LDMs). Despite their successes, a few have studied the surrogate model they used to generate AEs. In this paper, from the perspective of adversarial transferability, we investigate how the surrogate model's property influences the performance of AEs for LDMs. Specifically, we view the time-step sampling in the Monte-Carlo-based (MC-based) adversarial attack as selecting surrogate models. We find that the smoothness of surrogate models at different time steps differs, and we substantially improve the performance of the MC-based AEs by selecting smoother surrogate models. In the light of the theoretical framework on adversarial transferability in image classification, we also conduct a theoretical analysis to explain why smooth surrogate models can also boost AEs for LDMs. |
| title | Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2401.07087 |