Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models

22 May 2025

Papers citing "Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models"

6 / 6 papers shown

Title
On the Role of Attention Heads in Large Language Model Safety Zhenhong Zhou Haiyang Yu Xinghua Zhang Rongwu Xu Fei Huang Kun Wang Yang Liu Sihang Li Yongbin Li 112 9 0 17 Oct 2024
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting Yu Wang Xiaogeng Liu Yu-Feng Li Muhao Chen Chaowei Xiao AAML 77 57 0 14 Mar 2024
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts Yichen Gong Delong Ran Jinyuan Liu Conglei Wang Tianshuo Cong Anyu Wang Sisi Duan Xiaoyun Wang MLLM 211 147 0 09 Nov 2023
DocVQA: A Dataset for VQA on Document Images Minesh Mathew Dimosthenis Karatzas C. V. Jawahar 137 718 0 01 Jul 2020
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions Christopher Clark Kenton Lee Ming-Wei Chang Tom Kwiatkowski Michael Collins Kristina Toutanova 217 1,517 0 24 May 2019
SNIP: Single-shot Network Pruning based on Connection Sensitivity Namhoon Lee Thalaiyasingam Ajanthan Philip Torr VLM 257 1,199 0 04 Oct 2018