Jiaqi Li's Blog
Posts Categories Tags About
Jiaqi Li's Blog· Light
☰ Menu
Posts Categories Tags About

- Categories · Jailbreak Defence-

2025

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks October 31, 2025
Steering Llama 2 via Contrastive Activation Addition October 30, 2025
© Jiaqi Li | Powered by Hexo & Chic