pH试纸式选择性遗忘：一种钝但快速的机器遗忘诊断基线
pH-Strips for Selective Forgetting: A Blunt but Fast Diagnostic Baseline for Machine Unlearning
提供了一种免训练、仅需少量样本即可快速擦除模型中特定概念（如分类中的类别、生成中的风格）的诊断基线，视觉研究者可将其作为评估新遗忘方法效率与效果的快速试金石，或直接用于扩散模型的概念擦除。
原文依据 we propose a simple yet efficient training-free and retain-set-free MU algorithm designed explicitly as a diagnostic baseline
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论机器遗忘（MU）旨在从人工智能（AI）模型中擦除不良内容，对构建安全可信的AI系统至关重要。尽管已取得显著进展，基线MU方法依赖于在不包含待移除数据的情况下从头重新训练，计算成本高昂且经济上难以承受。为解决这一挑战，我们提出一种简单而高效的免训练且无需保留集的MU算法，明确设计为诊断基线：机器遗忘pH测试（MUpHT）。它旨在为未来的MU方法提供实用的评估参考。我们的方法从模型权重向量张成的空间中消除与不良概念相关的低维子空间，从而使模型对这些不良内容“失明”。此外，我们扩展了保留感知变体，通过利用在不良集和保留集上的广义瑞利商来处理纠缠特征，从而在保留知识与抑制不良知识之间实现高效权衡。我们的方法支持跨多种视觉任务的MU评估，包括分类、图像生成和多模态应用中的概念擦除。通过仅从少量样本即时生成遗忘后的模型，我们的方法可作为MU的快速试金石。
英文原文摘要 1364 字符
Machine Unlearning (MU), erasing undesirable content from Artificial Intelligence (AI) models, plays an essential role in developing safe and trustworthy AI systems.Despite notable advances, the baseline MU methods rely on retraining from scratch without the data to be removed, which is computationally expensive and financially prohibitive.To address this challenge, we propose a simple yet efficient training-free and retain-set-free MU algorithm designed explicitly as a diagnostic baseline: Machine Unlearning pH-Test (MUpHT).It is designed to serve as a practical evaluation reference for future MU methods.Our method eliminates the low dimensional subspaces associated with undesirable concepts from the space spanned by the model's weight vectors, thereby rendering the model "blind" to these undesirable contents. Additionally, we extend our retain-aware variant to handle entangled features by leveraging a generalized Rayleigh quotient over the undesirable and retain sets, enabling an efficient tradeoff between preserving retained knowledge and suppressing undesirable knowledge.Our method enables evaluation of MU across diverse visual tasks, including concept erasure for classification, image generation, and multimodal applications.By producing an unlearned model instantly from only a few samples, our method serves as a quick litmus test for MU.