Feb. 26, 2024, 5:46 a.m. | Yu Tian, Xiao Yang, Yinpeng Dong, Heming Yang, Hang Su, Jun Zhu

cs.CV updates on arXiv.org arxiv.org

arXiv:2402.15218v1 Announce Type: cross
Abstract: Extremely large image generators offer significant transformative potential across diverse sectors. It allows users to design specific prompts to generate realistic images through some black-box APIs. However, some studies reveal that image generators are notably susceptible to attacks and generate Not Suitable For Work (NSFW) contents by manually designed toxin texts, especially imperceptible to human observers. We urgently need a multitude of universal and transferable prompts to improve the safety of image generators, especially black-box-released …

abstract apis arxiv attacks box contents cs.cl cs.cr cs.cv design diverse generate generators image image generators images nsfw prompt prompts studies through type work

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