Li Yanchun, Li Zemin, Huang Long, Hu Lingzhi, Zeng Li, Shen Dongsu
School of Computer Science, Xiangtan University, Xiangtan, 411105, China; Hunan International Scientific and Technological Cooperation Base of Intelligent network, Xiangtan, 411105, China; Key Laboratory of Hunan Province for Internet of Things and Information Security, Xiangtan, 411105, China.
School of Computer Science, Xiangtan University, Xiangtan, 411105, China.
Neural Netw. 2025 Jul 18;192:107877. doi: 10.1016/j.neunet.2025.107877.
Recently, the employment of diffusion models for adversarial purification has attracted the attention due to their strong generalization ability towards defensive adversarial examples. However, the multi-step sampling required for the diffusion model results in time and resource consumption. To address these issues, we propose a novel One-Step Guided Diffusion Model (OSGD) for efficient adversarial purification. OSGD combines a one-step denoising process with a guiding strategy to accelerate sampling speed and achieve superior purification results. Specifically, OSGD utilizes a diffusion model for two rounds of one-step denoising, with the preliminary image obtained in the first round serving as the guidance signal for the second round. In the second round, the adversarial images are purified under the guidance of preliminary images to eliminate adversarial perturbations. We analyze the rationality of using preliminary denoised images as guidance signals and verify the effectiveness of this guidance strategy through experiments. Extensive experiments on Cifar10 and ImageNet using three attack methods, including PGD, AutoAttack, and BPDA+EOT, demonstrate that our method achieves the state-of-the-art performance in terms of accuracy and efficiency. Source code for this work is available at https://github.com/zmlix/OSGD.git.
最近，扩散模型在对抗性净化中的应用因其对防御性对抗样本的强大泛化能力而受到关注。然而，扩散模型所需的多步采样会导致时间和资源消耗。为了解决这些问题，我们提出了一种新颖的一步引导扩散模型（OSGD）用于高效的对抗性净化。OSGD将一步去噪过程与一种引导策略相结合，以加快采样速度并实现卓越的净化效果。具体而言，OSGD利用扩散模型进行两轮一步去噪，第一轮获得的初步图像用作第二轮的引导信号。在第二轮中，对抗性图像在初步图像的引导下进行净化，以消除对抗性扰动。我们分析了使用初步去噪图像作为引导信号的合理性，并通过实验验证了这种引导策略的有效性。在Cifar10和ImageNet上使用三种攻击方法（包括PGD、AutoAttack和BPDA + EOT）进行的大量实验表明，我们的方法在准确性和效率方面达到了当前的最优性能。这项工作的源代码可在https://github.com/zmlix/OSGD.git获取。
