Text-to-image diffusion models, such as Stable Diffusion, generate highly realistic images from text descriptions. However, the generation of certain content at such high quality raises concerns. A prominent issue is the accurate depiction of identifiable facial images, which could lead to malicious deepfake generation and privacy violations. In this paper, we propose Anonymization Prompt Learning (APL) to address this problem. Specifically, we train a learnable prompt prefix for text-to-image diffusion models, which forces the model to generate anonymized facial identities, even when prompted to produce images of specific individuals. Extensive quantitative and qualitative experiments demonstrate the successful anonymization performance of APL, which anonymizes any specific individuals without compromising the quality of non-identity-specific image generation. Furthermore, we reveal the plug-and-play property of the learned prompt prefix, enabling its effective application across different pretrained text-to-image models for transferrable privacy and security protection against the risks of deepfakes.

翻译：以 Stable Diffusion 为代表的文本到图像扩散模型能够根据文本描述生成高度逼真的图像。然而，此类高质量内容的生成也引发了担忧。一个突出的问题是模型可能生成可识别的人脸图像，这可能导致恶意深度伪造内容的产生和隐私侵犯。本文提出匿名化提示学习（APL）来解决这一问题。具体而言，我们为文本到图像扩散模型训练一个可学习的提示前缀，该前缀迫使模型生成匿名化的人脸身份，即使是在被提示生成特定个体图像时。大量的定量和定性实验证明了 APL 成功的匿名化性能，它能够在不对非身份特定图像生成质量造成损害的前提下，对任何特定个体进行匿名化处理。此外，我们揭示了所学提示前缀的即插即用特性，使其能够有效应用于不同的预训练文本到图像模型，从而提供可迁移的隐私和安全保护，以应对深度伪造风险。