Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Year
2025
Type(s)
Author(s)
Souradip Chakraborty Soumya Suvra Ghosal and Vaibhav Singh and Tianrui Guan and Mengdi Wang and Ahmad Beirami and Furong Huang and Alvaro Velasquez and Dinesh Manocha and Amrit Singh Bedi
Source
In Conference on Computer Vision and Pattern Recognition (CVPR), 2025, 2025
Url
https://arxiv.org/abs/2411.18688
BibTeX
BibTeX