arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.00623cs.CV
收藏

一致性净化:面向认证鲁棒性的高效扩散净化方法

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);University of Chicago(芝加哥大学);University of Michigan, Ann Arbor(密歇根大学安娜堡分校)

Yiquan Li, Zhongzhu Chen, Kun Jin, Jiongxiao Wang, Bo Li, Chaowei Xiao

AI总结:

本文针对扩散净化中效率与有效性的平衡问题,提出基于一致性模型的一致性净化方法,并通过LPIPS损失微调增强语义对齐,在单步计算下实现领先的认证鲁棒性与效率。

摘要:

扩散净化(Diffusion Purification),即利用扩散模型净化含噪图像,已被广泛用于通过随机平滑(randomized smoothing)增强认证鲁棒性。然而,现有框架往往难以在效率与有效性之间取得平衡。去噪扩散概率模型(DDPM)虽然提供了高效的单步净化,但难以确保净化后的图像位于数据流形上。相反,随机扩散模型能够有效地将净化图像置于数据流形上,但需要求解繁琐的随机微分方程;而其衍生方法概率流常微分方程(PF-ODE)虽然求解的是更简单的常微分方程,仍需要多个计算步骤。在本工作中,我们证明了一个理想的净化流程应当以单步方式生成位于数据流形上、且在语义上尽可能与原始图像对齐的净化图像,从而兼顾有效性与效率。为此,我们提出了一致性净化(Consistency Purification),一种相比先前工作在效率-有效性帕累托意义上更优的净化器。一致性净化采用一致性模型(consistency model),这是一种从PF-ODE蒸馏得到的单步生成模型,因此只需一次网络评估即可生成位于流形上的净化图像。然而,一致性模型并非为净化任务设计,因此其本身并不能保证净化图像与原始图像之间的语义对齐。为解决这一问题,我们进一步通过带LPIPS损失的一致性微调(Consistency Fine-tuning)对其进行改进,从而在保持净化图像位于数据流形上的同时实现更强的语义对齐。我们的综合实验表明,与基线方法相比,一致性净化框架在认证鲁棒性和效率方面均达到了最先进的水平。

英文摘要:

Diffusion Purification, purifying noised images with diffusion models, has been widely used for enhancing certified robustness via randomized smoothing. However, existing frameworks often grapple with the balance between efficiency and effectiveness. While the Denoising Diffusion Probabilistic Model (DDPM) offers an efficient single-step purification, it falls short in ensuring purified images reside on the data manifold. Conversely, the Stochastic Diffusion Model effectively places purified images on the data manifold but demands solving cumbersome stochastic differential equations, while its derivative, the Probability Flow Ordinary Differential Equation (PF-ODE), though solving simpler ordinary differential equations, still requires multiple computational steps. In this work, we demonstrated that an ideal purification pipeline should generate the purified images on the data manifold that are as much semantically aligned to the original images for effectiveness in one step for efficiency. Therefore, we introduced Consistency Purification, an efficiency-effectiveness Pareto superior purifier compared to the previous work. Consistency Purification employs the consistency model, a one-step generative model distilled from PF-ODE, thus can generate on-manifold purified images with a single network evaluation. However, the consistency model is designed not for purification thus it does not inherently ensure semantic alignment between purified and original images. To resolve this issue, we further refine it through Consistency Fine-tuning with LPIPS loss, which enables more aligned semantic meaning while keeping the purified images on data manifold. Our comprehensive experiments demonstrate that our Consistency Purification framework achieves state-of the-art certified robustness and efficiency compared to baseline methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑