Recently text-to-image models have gained widespread attention in the community due to their controllable and high-quality generation ability. However, the robustness of such models and their potential ethical issues have not been fully explored. In this paper, we introduce Universal Semantic Trigger, a meaningless token sequence that can be added at any location within the input text yet can induce generated images towards a preset semantic target.To thoroughly investigate it, we propose Semantic Gradient-based Search (SGS) framework. SGS automatically discovers the potential universal semantic triggers based on the given semantic targets. Furthermore, we design evaluation metrics to comprehensively evaluate semantic shift of images caused by these triggers. And our empirical analyses reveal that the mainstream open-source text-to-image models are vulnerable to our triggers, which could pose significant ethical threats. Our work contributes to a further understanding of text-to-image synthesis and helps users to automatically auditing their models before deployment.

翻译：摘要：近年来，文本到图像模型因其可控且高质量的生成能力在学术界受到广泛关注。然而，这类模型的鲁棒性及其潜在的伦理问题尚未得到充分探索。本文提出了通用语义触发器（Universal Semantic Trigger）的概念，这是一种无意义的令牌序列，可插入输入文本中的任意位置，却能引导生成的图像朝向预设的语义目标。为深入探究这一问题，我们提出了基于语义梯度的搜索（Semantic Gradient-based Search，SGS）框架。SGS能够根据给定的语义目标自动发现潜在的通用语义触发器。此外，我们设计了评估指标来全面衡量这些触发器引起的图像语义偏移。实证分析表明，主流的开源文本到图像模型易受我们的触发器攻击，这可能导致重大的伦理威胁。我们的工作有助于进一步理解文本到图像合成过程，并帮助用户在部署模型前进行自动化审计。