让生成模型忘记特定内容，同时保持其他能力。
Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
- 通过最大化生成图像的熵，使模型在处理禁止类别时输出噪声。
- 仅调整扩散过程的早期步骤，实现高效遗忘且保留整体性能。
- 相比现有方法，速度提升显著，适合需快速清除数据的场景。
我们提出SAFEMax，一种针对扩散模型的机器遗忘新方法。基于信息论原理，SAFEMax通过最大化生成图像的熵，使模型在遇到禁止类别时停止去噪过程，最终输出高斯噪声。该方法通过聚焦扩散过程的早期阶段——此时类别信息最为显著——来调控遗忘与保留的平衡。实验表明，SAFEMax在有效实现遗忘的同时，相较当前最优方法展现出显著的效率优势。
原文摘要 · Abstract (English)
We introduce SAFEMax, a novel method for Machine Unlearning in diffusion models. Grounded in information-theoretic principles, SAFEMax maximizes the entropy in generated images, causing the model to generate Gaussian noise when conditioned on impermissible classes by ultimately halting its denoising process. Also, our method controls the balance between forgetting and retention by selectively focusing on the early diffusion steps, where class-specific information is prominent. Our results demonstrate the effectiveness of SAFEMax and highlight its substantial efficiency gains over state-of-the-art methods.
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。