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

TL;DR

This paper introduces Hierarchical Safety Realignment, a lightweight method to restore safety in pruned large vision-language models by selectively restoring neurons in critical attention heads, improving safety performance after pruning.

Contribution

The paper proposes a novel hierarchical safety realignment technique that identifies and restores critical neurons within attention heads to recover safety in pruned LVLMs.

Findings

HSR significantly improves safety metrics across models

Selective neuron restoration outperforms baseline pruning methods

First approach explicitly targeting safety restoration in pruned LVLMs

Abstract

With the increasing size of Large Vision-Language Models (LVLMs), network pruning techniques aimed at compressing models for deployment in resource-constrained environments have garnered significant attention. However, we observe that pruning often leads to a degradation in safety performance. To address this issue, we present a novel and lightweight approach, termed Hierarchical Safety Realignment (HSR). HSR operates by first quantifying the contribution of each attention head to safety, identifying the most critical ones, and then selectively restoring neurons directly within these attention heads that play a pivotal role in maintaining safety. This process hierarchically realigns the safety of pruned LVLMs, progressing from the attention head level to the neuron level. We validate HSR across various models and pruning strategies, consistently achieving notable improvements in safety performance. To our knowledge, this is the first work explicitly focused on restoring safety in LVLMs post-pruning.