通过概率景观锐度分析扩散模型的记忆现象，提出早期检测与抑制方法。
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
- 用对数概率密度的锐度刻画记忆程度，解释已有指标有效性。
- 新指标可提前发现生成初期的记忆风险，定位问题更早。
- 基于锐度正则化优化初始噪声，有效降低记忆行为，适合安全生成场景。
本文提出一种几何框架，通过扩散模型中对数概率密度的锐度来分析记忆现象。我们从数学上证明了此前提出的基于得分差的记忆度量指标的有效性，该指标能准确量化概率景观的锐度。此外，我们提出了一个新记忆度量，用于捕捉潜在扩散模型在图像生成初始阶段的锐度特征，从而提供早期记忆风险预警。基于此度量，我们设计了一种缓解策略，在生成过程的初始噪声优化中引入锐度感知正则项，有效抑制记忆行为。代码已公开于 https://github.com/Dongjae0324/sharpness_memorization_diffusion。
原文摘要 · Abstract (English)
In this paper, we introduce a geometric framework to analyze memorization in diffusion models through the sharpness of the log probability density. We mathematically justify a previously proposed score-difference-based memorization metric by demonstrating its effectiveness in quantifying sharpness. Additionally, we propose a novel memorization metric that captures sharpness at the initial stage of image generation in latent diffusion models, offering early insights into potential memorization. Leveraging this metric, we develop a mitigation strategy that optimizes the initial noise of the generation process using a sharpness-aware regularization term. The code is publicly available at https://github.com/Dongjae0324/sharpness_memorization_diffusion.
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。