Skip to content
conftrace_

vision domain attack

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

malicious data curation (1) rejection learning (1) large language model (1) multimodal large language model (1) safety alignment (1) multimodal learning (1)

Papers

Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models? CVPR 2025