Adapter Shield：内置认证的统一框架，用于阻止未经授权的零样本图像到图像生成
Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation
针对零样本图像到图像生成中的身份/风格盗用，提出可逆加密嵌入加多目标对抗扰动，把图像编码器输出的嵌入推向指定加密模式；做扩散模型安全、水印或个性化生成防护的研究可直接复用这套「嵌入层加密+对抗偏移」思路。
原文依据 we design a multi-target adversarial perturbation method that actively shifts the original embeddings toward designated encrypted patterns
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着扩散模型的快速进展，图像合成已发展到零样本图像到图像生成的阶段：仅凭一张人像或一幅艺术作品，无需修改任何模型权重，即可实现对人脸身份或艺术风格的高保真复制。尽管这些技术显著拓展了创作可能性，但也带来了与知识产权侵权相关的重大风险，包括未经授权的身份克隆与风格模仿。为应对此类威胁，本工作提出 Adapter Shield，这是首个面向零样本生成场景、用于保护个人图像免遭滥用的通用且集成认证的解决方案。我们首先研究了当前零样本方法如何利用图像编码器从输入图像中提取嵌入，这些嵌入随后通过交叉注意力层被送入扩散模型的 UNet。受此机制启发，我们构建了一个可逆加密系统，依据不同的密钥将原始嵌入映射为不同的加密表示。授权用户可通过解密模块与正确密钥恢复真实嵌入，从而正常用于授权的生成任务。为实施保护，我们设计了一种多目标对抗扰动方法，主动将原始嵌入推向指定的加密模式。由此，受保护图像被嵌入一层防御层，确保未授权用户只能产生失真或加密的输出。大量评估表明，我们的方法在阻止未授权零样本图像合成方面优于现有最优防御方法，同时为经核验用户支持灵活且安全的访问控制。
英文原文摘要 1778 字符
With the rapid progress in diffusion models, image synthesis has advanced to the stage of zero-shot image-to-image generation, where high-fidelity replication of facial identities or artistic styles can be achieved using just one portrait or artwork, without modifying any model weights. Although these techniques significantly enhance creative possibilities, they also pose substantial risks related to intellectual property violations, including unauthorized identity cloning and stylistic imitation. To counter such threats, this work presents Adapter Shield, the first universal and authentication-integrated solution aimed at defending personal images from misuse in zero-shot generation scenarios. We first investigate how current zero-shot methods employ image encoders to extract embeddings from input images, which are subsequently fed into the UNet of diffusion models through cross-attention layers. Inspired by this mechanism, we construct a reversible encryption system that maps original embeddings into distinct encrypted representations according to different secret keys. The authorized users can restore the authentic embeddings via a decryption module and the correct key, enabling normal usage for authorized generation tasks. For protection purposes, we design a multi-target adversarial perturbation method that actively shifts the original embeddings toward designated encrypted patterns. Consequently, protected images are embedded with a defensive layer that ensures unauthorized users can only produce distorted or encrypted outputs. Extensive evaluations demonstrate that our method surpasses existing state-of-the-art defenses in blocking unauthorized zero-shot image synthesis, while supporting flexible and secure access control for verified users.