Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914685083713536 |
|---|---|
| author | Liu, Yi Yang, Guowei Deng, Gelei Chen, Feiyue Chen, Yuqi Shi, Ling Zhang, Tianwei Liu, Yang |
| author_facet | Liu, Yi Yang, Guowei Deng, Gelei Chen, Feiyue Chen, Yuqi Shi, Ling Zhang, Tianwei Liu, Yang |
| contents | With the prevalence of text-to-image generative models, their safety becomes a critical concern. adversarial testing techniques have been developed to probe whether such models can be prompted to produce Not-Safe-For-Work (NSFW) content. However, existing solutions face several challenges, including low success rate and inefficiency. We introduce Groot, the first automated framework leveraging tree-based semantic transformation for adversarial testing of text-to-image models. Groot employs semantic decomposition and sensitive element drowning strategies in conjunction with LLMs to systematically refine adversarial prompts. Our comprehensive evaluation confirms the efficacy of Groot, which not only exceeds the performance of current state-of-the-art approaches but also achieves a remarkable success rate (93.66%) on leading text-to-image models such as DALL-E 3 and Midjourney. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12100 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation Liu, Yi Yang, Guowei Deng, Gelei Chen, Feiyue Chen, Yuqi Shi, Ling Zhang, Tianwei Liu, Yang Computation and Language Artificial Intelligence Cryptography and Security Software Engineering With the prevalence of text-to-image generative models, their safety becomes a critical concern. adversarial testing techniques have been developed to probe whether such models can be prompted to produce Not-Safe-For-Work (NSFW) content. However, existing solutions face several challenges, including low success rate and inefficiency. We introduce Groot, the first automated framework leveraging tree-based semantic transformation for adversarial testing of text-to-image models. Groot employs semantic decomposition and sensitive element drowning strategies in conjunction with LLMs to systematically refine adversarial prompts. Our comprehensive evaluation confirms the efficacy of Groot, which not only exceeds the performance of current state-of-the-art approaches but also achieves a remarkable success rate (93.66%) on leading text-to-image models such as DALL-E 3 and Midjourney. |
| title | Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation |
| topic | Computation and Language Artificial Intelligence Cryptography and Security Software Engineering |
| url | https://arxiv.org/abs/2402.12100 |