Text-to-image diffusion models are nothing but a revolution, allowing anyone, even without design skills, to create realistic images from simple text inputs. With powerful personalization tools like DreamBooth, they can generate images of a specific person just by learning from his/her few reference images. However, when misused, such a powerful and convenient tool can produce fake news or disturbing content targeting any individual victim, posing a severe negative social impact. In this paper, we explore a defense system called Anti-DreamBooth against such malicious use of DreamBooth. The system aims to add subtle noise perturbation to each user's image before publishing in order to disrupt the generation quality of any DreamBooth model trained on these perturbed images. We investigate a wide range of algorithms for perturbation optimization and extensively evaluate them on two facial datasets over various text-to-image model versions. Despite the complicated formulation of DreamBooth and Diffusion-based text-to-image models, our methods effectively defend users from the malicious use of those models. Their effectiveness withstands even adverse conditions, such as model or prompt/term mismatching between training and testing. Our code will be available at \href{https://github.com/VinAIResearch/Anti-DreamBooth.git}{https://github.com/VinAIResearch/Anti-DreamBooth.git}.

翻译：文本到图像扩散模型堪称一场革命，使得即便不具备设计技能的任何人，也能通过简单文本输入生成逼真图像。借助如DreamBooth等强大的个性化工具，仅需学习目标人物的少数几张参考图像即可生成其专属图像。然而，当该强大便捷的工具被滥用时，可生成针对特定个人的虚假新闻或令人不安的内容，造成严重负面社会影响。本文探索了一种名为Anti-DreamBooth的防御系统，用于对抗DreamBooth的此类恶意使用。该系统旨在于用户图像发布前，向每张图像添加微妙的噪声扰动，以破坏基于这些扰动图像训练的任何DreamBooth模型的生成质量。我们研究了多种扰动优化算法，并在两个面部数据集上针对不同版本的文本到图像模型进行了全面评估。尽管DreamBooth及基于扩散的文本到图像模型公式复杂，我们的方法仍能有效防御用户免受这些模型恶意使用的影响。其有效性甚至能抵御不利条件，例如训练与测试之间的模型或提示/术语不匹配。我们的代码将在\href{https://github.com/VinAIResearch/Anti-DreamBooth.git}{https://github.com/VinAIResearch/Anti-DreamBooth.git}开源。