Adv-CPG：一种带有面部对抗攻击的定制肖像生成框架
Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks
AI总结：
本文提出 Adv-CPG 框架，首次将面部对抗攻击引入定制肖像生成，通过轻量级局部 ID 加密器、加密增强器和多模态图像定制器实现隐私保护与细粒度个性化生成，实验表明其攻击成功率优于现有方法。
摘要：
近年来，以一张面部图像和一段文本提示为输入的定制肖像生成（Customized Portrait Generation, CPG）方法引起了广泛关注。尽管这些方法能够生成高保真度的肖像，但它们无法防止生成的肖像被恶意人脸识别系统跟踪和滥用。为了解决这一问题，本文提出了一种带有面部对抗攻击的定制肖像生成框架（Adv-CPG）。具体而言，为了实现面部隐私保护，我们设计了一个轻量级局部身份（ID）加密器和一个加密增强器。它们分别通过直接注入目标身份和添加额外的身份引导来实现渐进式双层加密保护。此外，为了实现细粒度和个性化的肖像生成，我们开发了一个多模态图像定制器，能够生成可控的细粒度面部特征。据我们所知，Adv-CPG 是首个将面部对抗攻击引入 CPG 的研究。大量实验证明了 Adv-CPG 的优越性，例如，与最先进的基于噪声的攻击方法和无约束攻击方法相比，所提出的 Adv-CPG 的平均攻击成功率分别提高了 28.1% 和 2.86%。
英文摘要：
Recent Customized Portrait Generation (CPG) methods, taking a facial image and a textual prompt as inputs, have attracted substantial attention. Although these methods generate high-fidelity portraits, they fail to prevent the generated portraits from being tracked and misused by malicious face recognition systems. To address this, this paper proposes a Customized Portrait Generation framework with facial Adversarial attacks (Adv-CPG). Specifically, to achieve facial privacy protection, we devise a lightweight local ID encryptor and an encryption enhancer. They implement progressive double-layer encryption protection by directly injecting the target identity and adding additional identity guidance, respectively. Furthermore, to accomplish fine-grained and personalized portrait generation, we develop a multi-modal image customizer capable of generating controlled fine-grained facial features. To the best of our knowledge, Adv-CPG is the first study that introduces facial adversarial attacks into CPG. Extensive experiments demonstrate the superiority of Adv-CPG, e.g., the average attack success rate of the proposed Adv-CPG is 28.1% and 2.86% higher compared to the SOTA noise-based attack methods and unconstrained attack methods, respectively.
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。
