Recently, machine unlearning approaches have been proposed to remove sensitive information from well-trained large models. However, most existing methods are tailored for LLMs, while MLLM-oriented unlearning remains at its early stage. Inspired by recent studies exploring the internal mechanisms of MLLMs, we propose to disentangle the visual and textual knowledge embedded within MLLMs and introduce a dedicated approach to selectively erase target visual knowledge while preserving textual knowledge. Unlike previous unlearning methods that rely on output-level supervision, our approach introduces a Visual Knowledge Distillation (VKD) scheme, which leverages intermediate visual representations within the MLLM as supervision signals. This design substantially enhances both unlearning effectiveness and model utility. Moreover, since our method only fine-tunes the visual components of the MLLM, it offers significant efficiency advantages. Extensive experiments demonstrate that our approach outperforms state-of-the-art unlearning methods in terms of both effectiveness and efficiency. Moreover, we are the first to evaluate the robustness of MLLM unlearning against relearning attacks.

翻译：近年来，机器遗忘方法被提出用于从训练完备的大型模型中移除敏感信息。然而，现有方法大多针对纯文本大语言模型（LLMs）设计，面向多模态大语言模型（MLLMs）的遗忘研究仍处于早期阶段。受近期探索MLLM内部机制的研究启发，我们提出解耦MLLM中嵌入的视觉与文本知识，并引入一种专门方法以选择性擦除目标视觉知识，同时保留文本知识。与以往依赖输出层监督的遗忘方法不同，本方法提出视觉知识蒸馏（VKD）方案，利用MLLM内部的中间视觉表征作为监督信号。该设计显著提升了遗忘效果与模型实用性的平衡。此外，由于本方法仅对MLLM的视觉组件进行微调，在计算效率上具有显著优势。大量实验表明，本方法在效果与效率方面均优于现有最先进的遗忘方法。同时，我们首次系统评估了MLLM遗忘方法针对再学习攻击的鲁棒性。