取消不可提示的内容：扩散模型中的无提示实例取消学习
Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models
AI总结：
本文提出一种无提示的扩散模型实例取消学习方法，通过图像编辑、时间步加权和梯度手术，有效消除不可提示的不受欢迎输出，如面孔和文化误判，同时保持模型完整性。
摘要：
机器取消学习旨在从训练模型中移除特定输出，通常在概念层面，例如忘记特定名人的所有出现或通过文本提示过滤内容。然而，许多不受欢迎的输出，如个人的面孔或文化上或事实上有误的生成，通常无法通过文本提示指定。我们针对这一未被充分探索的设置，即实例取消学习，用于那些不受欢迎但不可提示的输出，目标是在保留其余内容的同时选择性地忘记目标输出。为此，我们介绍了一种有效的替代方法，利用图像编辑、时间步感知加权和梯度手术来引导训练的扩散模型朝着忘记特定输出的方向发展。在条件（Stable Diffusion 3）和无条件（DDPM-CelebA）扩散模型上的实验表明，我们的无提示方法能够独特地取消不可提示的输出，如面孔和文化上不准确的描绘，同时保持完整性，不同于基于提示和无提示的基线方法。我们提出的方法将成为扩散模型提供者确保隐私保护和伦理合规的实用修复方案。
英文摘要：
Machine unlearning aims to remove specific outputs from trained models, often at the concept level, such as forgetting all occurrences of a particular celebrity or filtering content via text prompts. However, many undesired outputs, such as an individual's face or generations culturally or factually misinterpreted, cannot often be specified by text prompts. We address this underexplored setting of instance unlearning for outputs that are undesired but unpromptable, where the goal is to forget target outputs selectively while preserving the rest. To this end, we introduce an effective surrogate-based unlearning method that leverages image editing, timestep-aware weighting, and gradient surgery to guide trained diffusion models toward forgetting specific outputs. Experiments on conditional (Stable Diffusion 3) and unconditional (DDPM-CelebA) diffusion models demonstrate that our prompt-free method uniquely unlearns unpromptable outputs, such as faces and culturally inaccurate depictions, with preserved integrity, unlike prompt-based and prompt-free baselines. Our proposed method would serve as a practical hotfix for diffusion model providers to ensure privacy protection and ethical compliance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
