Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.00778 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916982524215296 |
|---|---|
| author | Hong, Seunghoo Son, Geonho Lee, Juhun Woo, Simon S. |
| author_facet | Hong, Seunghoo Son, Geonho Lee, Juhun Woo, Simon S. |
| contents | Diffusion models have shown to be strong representation learners, showcasing state-of-the-art performance across multiple domains. Aside from accelerated sampling, DDIM also enables the inversion of real images back to their latent codes. A direct inheriting application of this inversion operation is real image editing, where the inversion yields latent trajectories to be utilized during the synthesis of the edited image. Unfortunately, this practical tool has enabled malicious users to freely synthesize misinformative or deepfake contents with greater ease, which promotes the spread of unethical and abusive, as well as privacy-, and copyright-infringing contents. While defensive algorithms such as AdvDM and Photoguard have been shown to disrupt the diffusion process on these images, the misalignment between their objectives and the iterative denoising trajectory at test time results in weak disruptive performance.In this work, we present the DDIM Inversion Attack (DIA) that attacks the integrated DDIM trajectory path. Our results support the effective disruption, surpassing previous defensive methods across various editing methods. We believe that our frameworks and results can provide practical defense methods against the malicious use of AI for both the industry and the research community. Our code is available here: https://anonymous.4open.science/r/DIA-13419/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00778 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models Hong, Seunghoo Son, Geonho Lee, Juhun Woo, Simon S. Artificial Intelligence Diffusion models have shown to be strong representation learners, showcasing state-of-the-art performance across multiple domains. Aside from accelerated sampling, DDIM also enables the inversion of real images back to their latent codes. A direct inheriting application of this inversion operation is real image editing, where the inversion yields latent trajectories to be utilized during the synthesis of the edited image. Unfortunately, this practical tool has enabled malicious users to freely synthesize misinformative or deepfake contents with greater ease, which promotes the spread of unethical and abusive, as well as privacy-, and copyright-infringing contents. While defensive algorithms such as AdvDM and Photoguard have been shown to disrupt the diffusion process on these images, the misalignment between their objectives and the iterative denoising trajectory at test time results in weak disruptive performance.In this work, we present the DDIM Inversion Attack (DIA) that attacks the integrated DDIM trajectory path. Our results support the effective disruption, surpassing previous defensive methods across various editing methods. We believe that our frameworks and results can provide practical defense methods against the malicious use of AI for both the industry and the research community. Our code is available here: https://anonymous.4open.science/r/DIA-13419/. |
| title | DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.00778 |