ID-Cloak：针对个性化文本到图像生成的身份特定伪装设计
ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation
AI总结：
针对个性化文本到图像生成的隐私问题，提出ID-Cloak方法，首次建模身份子空间并设计身份特定伪装，保护特定身份的所有图像，为现实隐私保护提供有效通用方案。
摘要：
个性化文本到图像模型允许用户从几张参考照片生成新概念的图像，从而引发了关于公民隐私的重大担忧。尽管已开发出多种反个性化技术，但这些方法通常假设防御者能够为每个特定图像设计对应的隐私伪装。然而，由于在线共享的大量个人图像，特定图像方法在实际应用中受到限制。为解决这一问题，我们首次研究身份特定伪装（ID-Cloak）的创建，以保护属于特定身份的所有图像。具体而言，我们首先建模一个保留个人共性的身份子空间，并学习多样化上下文以捕捉待保护的图像分布。然后，我们使用提出的新目标设计身份特定伪装，该目标鼓励伪装引导模型偏离其子空间内的正常输出。大量实验表明，生成的通用伪装能有效保护图像。我们相信，我们的方法以及提出的身份特定伪装设置，标志着现实隐私保护领域的显著进步。
英文摘要：
Personalized text-to-image models allow users to generate images of new concepts from several reference photos, thereby leading to critical concerns regarding civil privacy. Although several anti-personalization techniques have been developed, these methods typically assume that defenders can afford to design a privacy cloak corresponding to each specific image. However, due to extensive personal images shared online, image-specific methods are limited by real-world practical applications. To address this issue, we are the first to investigate the creation of identity-specific cloaks (ID-Cloak) that safeguard all images belong to a specific identity. Specifically, we first model an identity subspace that preserves personal commonalities and learns diverse contexts to capture the image distribution to be protected. Then, we craft identity-specific cloaks with the proposed novel objective that encourages the cloak to guide the model away from its normal output within the subspace. Extensive experiments show that the generated universal cloak can effectively protect the images. We believe our method, along with the proposed identity-specific cloak setting, marks a notable advance in realistic privacy protection.
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。
