Adv-Diffusion：基于潜在扩散模型的不可感知对抗性人脸身份攻击
Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model
AI总结：
本文提出Adv-Diffusion框架，利用潜在扩散模型在潜在空间生成不可感知的对抗性身份扰动，通过身份敏感条件扩散和自适应强度算法，在FFHQ和CelebA-HQ上实现高迁移性和隐蔽性的攻击。
摘要：
对抗性攻击涉及向源图像添加扰动，以导致目标模型错误分类，这展示了攻击人脸识别模型的潜力。现有的对抗性人脸图像生成方法由于较低的迁移性和较高的可检测性，仍无法实现令人满意的性能。在本文中，我们提出了一个统一框架Adv-Diffusion，它可以在潜在空间而非原始像素空间中生成不可感知的对抗性身份扰动，利用潜在扩散模型的强大修复能力来生成逼真的对抗性图像。具体来说，我们提出了身份敏感的条件扩散生成模型，以在周围环境中生成语义扰动。所设计的基于自适应强度的对抗性扰动算法可以确保攻击的迁移性和隐蔽性。在公开的FFHQ和CelebA-HQ数据集上进行的大量定性和定量实验证明，所提出的方法在无需额外生成模型训练过程的情况下，相较于最先进的方法实现了优越的性能。源代码可在https://github.com/kopper-xdu/Adv-Diffusion获取。
英文摘要：
Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods still can't achieve satisfactory performance because of low transferability and high detectability. In this paper, we propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space, which utilizes strong inpainting capabilities of the latent diffusion model to generate realistic adversarial images. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness. Extensive qualitative and quantitative experiments on the public FFHQ and CelebA-HQ datasets prove the proposed method achieves superior performance compared with the state-of-the-art methods without an extra generative model training process. The source code is available at https://github.com/kopper-xdu/Adv-Diffusion.
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。
