提出动态选择目标的消融方法，减少扩散模型中概念删除的副作用。
Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
- 基于概念图谱动态寻找最优消融目标，而非固定通用目标。
- 实验表明，新方法在保留无关概念上优于现有技术。
- 适合需要精准控制生成内容安全性的研究人员使用。
概念消融已成为缓解扩散模型生成有害内容风险的有前景技术，通过选择性地遗忘不良概念来实现。以往方法通常将特定概念映射到固定的通用概念（如中性概念或空提示），但这种方法忽略了删除一个概念对其他概念的影响。本文将概念空间建模为图结构，实证分析了删除某一概念对剩余概念的影响。研究发现，概念间的影响力具有局部性特征。基于此，我们提出自适应引导消融（AGE）方法，能动态为每个不良概念选择最优目标，最大限度减少意外副作用。实验结果表明，AGE在保持无关概念完整性的同时，显著优于当前最先进的消融方法。代码已公开于 https://github.com/tuananhbui89/Adaptive-Guided-Erasure。
原文摘要 · Abstract (English)
Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models by selectively unlearning undesirable concepts. The common principle of previous works to remove a specific concept is to map it to a fixed generic concept, such as a neutral concept or just an empty text prompt. In this paper, we demonstrate that this fixed-target strategy is suboptimal, as it fails to account for the impact of erasing one concept on the others. To address this limitation, we model the concept space as a graph and empirically analyze the effects of erasing one concept on the remaining concepts. Our analysis uncovers intriguing geometric properties of the concept space, where the influence of erasing a concept is confined to a local region. Building on this insight, we propose the Adaptive Guided Erasure (AGE) method, which \emph{dynamically} selects optimal target concepts tailored to each undesirable concept, minimizing unintended side effects. Experimental results show that AGE significantly outperforms state-of-the-art erasure methods on preserving unrelated concepts while maintaining effective erasure performance. Our code is published at {https://github.com/tuananhbui89/Adaptive-Guided-Erasure}.
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。