让扩散模型自动防复学，防止被恶意微调恢复禁用内容
Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
- 通过元学习机制让模型在微调时自毁相关概念
- 实测在Stable Diffusion中有效阻止禁用概念复现
- 适合关注模型安全与版权保护的研究者
随着基于扩散模型的内容生成快速发展，如何从预训练模型中移除有害或受版权保护的概念以防止滥用成为重要课题。然而，即使模型已正确执行去学习（unlearning），恶意微调仍可能导致其重新学习被移除的概念。这部分源于某些保留的良性概念（如“皮肤”）与被移除概念（如“裸露”）存在关联，从而在微调过程中促进复现。为此，本文提出扩散模型上的元去学习（Meta-Unlearning）框架。其核心思想是：元去学习后的模型在正常使用时表现如未学习状态；若遭恶意微调，其中保留的良性概念将触发自我摧毁，阻断被移除概念的复现。该框架兼容多数现有去学习方法，仅需添加一个易实现的元目标。我们在Stable Diffusion-v1-4和SDXL上进行实验验证，并开展大量消融研究。代码已开源。
原文摘要 · Abstract (English)
With the rapid progress of diffusion-based content generation, significant efforts are being made to unlearn harmful or copyrighted concepts from pretrained diffusion models (DMs) to prevent potential model misuse. However, it is observed that even when DMs are properly unlearned before release, malicious finetuning can compromise this process, causing DMs to relearn the unlearned concepts. This occurs partly because certain benign concepts (e.g., "skin") retained in DMs are related to the unlearned ones (e.g., "nudity"), facilitating their relearning via finetuning. To address this, we propose meta-unlearning on DMs. Intuitively, a meta-unlearned DM should behave like an unlearned DM when used as is; moreover, if the meta-unlearned DM undergoes malicious finetuning on unlearned concepts, the related benign concepts retained within it will be triggered to self-destruct, hindering the relearning of unlearned concepts. Our meta-unlearning framework is compatible with most existing unlearning methods, requiring only the addition of an easy-to-implement meta objective. We validate our approach through empirical experiments on meta-unlearning concepts from Stable Diffusion models (SD-v1-4 and SDXL), supported by extensive ablation studies. Our code is available at https://github.com/sail-sg/Meta-Unlearning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。