With the wide deployment of multimodal learning systems (MMLS) in real-world scenarios, safety concerns have become increasingly prominent. The absence of systematic research into their safety is a significant barrier to progress in this field. To bridge the gap, we present the first taxonomy for MMLS safety, identifying four essential pillars of these concerns. Leveraging this taxonomy, we conduct in-depth reviews for each pillar, highlighting key limitations based on the current state of development. Finally, we pinpoint unique challenges in MMLS safety and provide potential directions for future research.

翻译：随着多模态学习系统（MMLS）在实际场景中的广泛应用，其安全问题日益凸显。由于缺乏对其安全性的系统性研究，这已成为该领域发展的重大障碍。为填补这一空白，我们提出了首个针对MMLS安全性的分类体系，识别出四类核心安全关切。基于该分类体系，我们对每类关切进行了深入综述，并依据当前发展状况指出了关键局限性。最后，我们明确了MMLS安全领域的独特挑战，并为未来研究提供了潜在方向。