为单步生成模型设计了高效类遗忘方法，解决安全问题。
Unlearning for One-Step Generative Models via Unbalanced Optimal Transport
- 基于不平衡最优传输，实现类遗忘与生成质量的平衡
- 在CIFAR-10和ImageNet-256上实现更高遗忘成功率与更优生成质量
- 适合需要安全可控生成模型的研究者与应用开发者
近年来，单步生成框架（如流映射模型）通过单次前向传播学习噪声到数据的直接映射，显著提升了图像生成效率。然而，确保这些强大生成器安全性的机器遗忘尚未被探索。现有扩散模型遗忘方法因依赖多步迭代去噪过程，与单步模型天然不兼容。本文提出UOT-Unlearn，一种基于不平衡最优传输（UOT）的即插即用类遗忘框架。该方法将遗忘建模为遗忘代价与f-散度惩罚之间的权衡：前者抑制目标类概率，后者通过放松边缘约束保持整体生成保真度。借助UOT，被遗忘类的概率质量可平滑重分配至剩余类别，避免坍缩为低质或噪声样本。在CIFAR-10和ImageNet-256上的实验表明，该框架在遗忘成功率（PUL）和保留质量（u-FID）方面均显著优于基线。
原文摘要 · Abstract (English)
Recent advances in one-step generative frameworks, such as flow map models, have significantly improved the efficiency of image generation by learning direct noise-to-data mappings in a single forward pass. However, machine unlearning for ensuring the safety of these powerful generators remains entirely unexplored. Existing diffusion unlearning methods are inherently incompatible with these one-step models, as they rely on a multi-step iterative denoising process. In this work, we propose UOT-Unlearn, a novel plug-and-play class unlearning framework for one-step generative models based on the Unbalanced Optimal Transport (UOT). Our method formulates unlearning as a principled trade-off between a forget cost, which suppresses the target class, and an $f$-divergence penalty, which preserves overall generation fidelity via relaxed marginal constraints. By leveraging UOT, our method enables the probability mass of the forgotten class to be smoothly redistributed to the remaining classes, rather than collapsing into low-quality or noise-like samples. Experimental results on CIFAR-10 and ImageNet-256 demonstrate that our framework achieves superior unlearning success (PUL) and retention quality (u-FID), significantly outperforming baselines.
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。