UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers

Duo Peng; Qiuhong Ke; Jun Liu

2024 ICML ICML 2024

UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Vision

Authors

Duo Peng, Qiuhong Ke, Jun Liu

Topics

Machine Learning > Optimization & Theory > Optimization Deep Learning > Models > Generative Models Computer Vision > Generation > Image Generation

Keywords

gradient-based optimization text-to-image generation prompt attack stealthiness semantic-enhancing learning sphere-probing learning

Download PDF