Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918122004414464 |
|---|---|
| author | Yan, Song Wei, Hui Fei, Jinlong Yang, Guoliang Zhao, Zhengyu Wang, Zheng |
| author_facet | Yan, Song Wei, Hui Fei, Jinlong Yang, Guoliang Zhao, Zhengyu Wang, Zheng |
| contents | Various (text) prompt filters and (image) safety checkers have been implemented to mitigate the misuse of Text-to-Image (T2I) models in creating Not-Safe-For-Work (NSFW) content. In order to expose potential security vulnerabilities of such safeguards, multimodal jailbreaks have been studied. However, existing jailbreaks are limited to prompt-specific and image-specific perturbations, which suffer from poor scalability and time-consuming optimization. To address these limitations, we propose Universally Unfiltered and Unseen (U3)-Attack, a multimodal jailbreak attack method against T2I safeguards. Specifically, U3-Attack optimizes an adversarial patch on the image background to universally bypass safety checkers and optimizes a safe paraphrase set from a sensitive word to universally bypass prompt filters while eliminating redundant computations. Extensive experimental results demonstrate the superiority of our U3-Attack on both open-source and commercial T2I models. For example, on the commercial Runway-inpainting model with both prompt filter and safety checker, our U3-Attack achieves $~4\times$ higher success rates than the state-of-the-art multimodal jailbreak attack, MMA-Diffusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05658 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards Yan, Song Wei, Hui Fei, Jinlong Yang, Guoliang Zhao, Zhengyu Wang, Zheng Cryptography and Security Computer Vision and Pattern Recognition Multimedia Various (text) prompt filters and (image) safety checkers have been implemented to mitigate the misuse of Text-to-Image (T2I) models in creating Not-Safe-For-Work (NSFW) content. In order to expose potential security vulnerabilities of such safeguards, multimodal jailbreaks have been studied. However, existing jailbreaks are limited to prompt-specific and image-specific perturbations, which suffer from poor scalability and time-consuming optimization. To address these limitations, we propose Universally Unfiltered and Unseen (U3)-Attack, a multimodal jailbreak attack method against T2I safeguards. Specifically, U3-Attack optimizes an adversarial patch on the image background to universally bypass safety checkers and optimizes a safe paraphrase set from a sensitive word to universally bypass prompt filters while eliminating redundant computations. Extensive experimental results demonstrate the superiority of our U3-Attack on both open-source and commercial T2I models. For example, on the commercial Runway-inpainting model with both prompt filter and safety checker, our U3-Attack achieves $~4\times$ higher success rates than the state-of-the-art multimodal jailbreak attack, MMA-Diffusion. |
| title | Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards |
| topic | Cryptography and Security Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2508.05658 |