Skip to content
conftrace_
2024 ICML ICML 2024

Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

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.

Authors

Yongshuo Zong, Ondrej Bohdal, Tingyang Yu, Yongxin Yang, Timothy Hospedales

Topics

Artificial Intelligence > Core AI > AI Safety Artificial Intelligence > Core AI > Multimodal Learning Artificial Intelligence > Core AI > Large Language Models

Keywords

harmful content safety alignment jailbreaking attack black-box adversarial attack vision large language model vlguard dataset
Download PDF