Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models
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_ | 1866908630540877824 |
|---|---|
| author | Cheng, Hao Xiao, Erjia Wang, Yichi Zhang, Lingfeng Zhang, Qiang Cao, Jiahang Xu, Kaidi Sun, Mengshu Hao, Xiaoshuai Gu, Jindong Xu, Renjing |
| author_facet | Cheng, Hao Xiao, Erjia Wang, Yichi Zhang, Lingfeng Zhang, Qiang Cao, Jiahang Xu, Kaidi Sun, Mengshu Hao, Xiaoshuai Gu, Jindong Xu, Renjing |
| contents | Current Cross-Modality Generation Models (GMs) demonstrate remarkable capabilities in various generative tasks. Given the ubiquity and information richness of vision modality inputs in real-world scenarios, Cross-Vision tasks, encompassing Vision-Language Perception (VLP) and Image-to-Image (I2I), have attracted significant attention. Large Vision Language Models (LVLMs) and I2I Generation Models (GMs) are employed to handle VLP and I2I tasks, respectively. Previous research indicates that printing typographic words into input images significantly induces LVLMs and I2I GMs to produce disruptive outputs that are semantically aligned with those words. Additionally, visual prompts, as a more sophisticated form of typography, are also revealed to pose security risks to various applications of cross-vision tasks. However, the specific characteristics of the threats posed by visual prompts remain underexplored. In this paper, to comprehensively investigate the performance impact induced by Typographic Visual Prompt Injection (TVPI) in various LVLMs and I2I GMs, we propose the Typographic Visual Prompts Injection Dataset and thoroughly evaluate the TVPI security risks on various open-source and closed-source LVLMs and I2I GMs under visual prompts with different target semantics, deepening the understanding of TVPI threats. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11519 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models Cheng, Hao Xiao, Erjia Wang, Yichi Zhang, Lingfeng Zhang, Qiang Cao, Jiahang Xu, Kaidi Sun, Mengshu Hao, Xiaoshuai Gu, Jindong Xu, Renjing Computer Vision and Pattern Recognition Computation and Language Current Cross-Modality Generation Models (GMs) demonstrate remarkable capabilities in various generative tasks. Given the ubiquity and information richness of vision modality inputs in real-world scenarios, Cross-Vision tasks, encompassing Vision-Language Perception (VLP) and Image-to-Image (I2I), have attracted significant attention. Large Vision Language Models (LVLMs) and I2I Generation Models (GMs) are employed to handle VLP and I2I tasks, respectively. Previous research indicates that printing typographic words into input images significantly induces LVLMs and I2I GMs to produce disruptive outputs that are semantically aligned with those words. Additionally, visual prompts, as a more sophisticated form of typography, are also revealed to pose security risks to various applications of cross-vision tasks. However, the specific characteristics of the threats posed by visual prompts remain underexplored. In this paper, to comprehensively investigate the performance impact induced by Typographic Visual Prompt Injection (TVPI) in various LVLMs and I2I GMs, we propose the Typographic Visual Prompts Injection Dataset and thoroughly evaluate the TVPI security risks on various open-source and closed-source LVLMs and I2I GMs under visual prompts with different target semantics, deepening the understanding of TVPI threats. |
| title | Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2503.11519 |