all AI news
Universal Prompt Optimizer for Safe Text-to-Image Generation
Feb. 19, 2024, 5:45 a.m. | Zongyu Wu, Hongcheng Gao, Yueze Wang, Xiang Zhang, Suhang Wang
cs.CV updates on arXiv.org arxiv.org
Abstract: Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe content like sexual, harassment and illegal-activity images. Existing studies based on image checker, model fine-tuning and embedding blocking are impractical in real-world applications. Hence, \textit{we propose the first universal prompt optimizer for safe T2I generation in black-box scenario}. We first construct a dataset consisting of toxic-clean prompt pairs by GPT-3.5 …
abstract applications arxiv blocking cs.cl cs.cv embedding fine-tuning generate harassment image image generation images model fine-tuning performance prompt prompts studies text text-to-image textual type vulnerable world
More from arxiv.org / cs.CV updates on arXiv.org
Compact 3D Scene Representation via Self-Organizing Gaussian Grids
1 day, 12 hours ago |
arxiv.org
Fingerprint Matching with Localized Deep Representation
1 day, 12 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne