通过对抗训练提升扩散模型的生成鲁棒性，解决训练与推理分布不一致问题。
Improved Diffusion-based Generative Model with Better Adversarial Robustness
- 用分布鲁棒优化理论证明扩散模型存在训练-推理分布差异。
- 对扩散模型和一致性模型均采用高效对抗训练，显著提升鲁棒性。
- 适合关注生成模型安全性与稳定性研究的研究者。
扩散概率模型在生成任务中取得了显著成功，但其训练与采样过程存在分布不匹配问题：去噪过程中，训练阶段与推理阶段的输入数据分布不一致，可能导致生成结果不准确。本文分析了扩散模型的训练目标，从理论上证明该问题可通过分布鲁棒优化（DRO）缓解，而DRO等价于对扩散模型进行基于鲁棒性的对抗训练（AT）。进一步地，针对近期提出的统一模型（Consistency Model, CM），本文证明其训练目标同样存在分布不匹配问题，亦可通过对抗训练缓解。基于此，本文提出在扩散模型和一致性模型上高效执行对抗训练。大量实证研究验证了该方法的有效性，代码已开源。
原文摘要 · Abstract (English)
Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mismatch. During the denoising process, the input data distributions differ between the training and inference stages, potentially leading to inaccurate data generation. To obviate this, we analyze the training objective of DPMs and theoretically demonstrate that this mismatch can be alleviated through Distributionally Robust Optimization (DRO), which is equivalent to performing robustness-driven Adversarial Training (AT) on DPMs. Furthermore, for the recently proposed Consistency Model (CM), which distills the inference process of the DPM, we prove that its training objective also encounters the mismatch issue. Fortunately, this issue can be mitigated by AT as well. Based on these insights, we propose to conduct efficient AT on both DPM and CM. Finally, extensive empirical studies validate the effectiveness of AT in diffusion-based models. The code is available at https://github.com/kugwzk/AT_Diff.
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。